Awesome 3D Gaussian Splatting Resources
A curated list of papers and open-source resources focused on 3D Gaussian Splatting, intended to keep pace with the anticipated surge of research in the coming months. If you have any additions or suggestions, feel free to contribute. Additional resources like blog posts, videos, etc. are also welcome.
Table of contents
Oct 24, 2024
- Added 2 papers: IGS, V^3
Oct 16, 2024
- Added one paper:DGD
Sept 07, 2024
- Added one paper:MoDGS
May 10, 2024
- Added 18 papers: Z-Splat, Dual-Camera, StylizedGS, Hash3D, Revisiting Densification, Gaussian Pancakes, 3D-aware Deformable Gaussians, SpikeNVS, Zero-shot PC completion, SplatPose, DreamScene360, RealmDreamer, Gaussian-ILC, Reinforcment Learning with GGS, GoMAvatar, OccGaussian, LoopGaussian, Review
April 11, 2024
- Code release of latentSplat
April 9, 2024
- Added 1 paper: EgoLifter
April 8, 2024
- Added 3 papers: Robust Gaussian Splatting, SC4D, and MM-Gaussian
April 5, 2024
- Added 5 papers: Surface Reconstruction, TCLC-GS, GaSpCT, OmniGS, and Per-Gaussian Embedding,
- Fixes
April 2, 2024
- Added 11 papers: HO, SGD, HGS, Snap-it, InstantSplat, 3DGSR, MM3DGS, HAHA, CityGaussain, Mirror-3DGS, and Feature Splatting
March 30, 2024
- Added 8 papers: Modeling uncertainty, GRM, Gamba, CoherentGS, TOGS, SA-GS, and GaussianCube
March 27, 2024
- Added Other Implementation: 360-gaussian-splatting
- CVPR '24 labels added
- Added 5 papers: Comp4D, DreamPolisher, DN-Splatter, 2D GS, and Octree-GS
March 26, 2024
- Added 13 paper: latentSplat, GS on the Move, RadSplat, Mini-Splatting, SyncTweedies, HAC, STAG4D, EndoGSLAM, Pixel-GS, Semantic Gaussians, Gaussian in the Wild, CG-SLAM, and GSDF
March 24, 2024:
- Added paper: Gaussian Frosting
March 20, 2024:
- Added 4 papers: GVGEN, HUGS, RGBD GS-ICP SLAM, and High-Fidelity SLAM
March 19, 2024:
- Added Pointrix
- Added 3DGS tutorial by the original authors
- Added GauStudio
- Added 23 papers: Touch-GS, GGRt, FDGaussian, SWAG, Den-SOFT, Gaussian-Flow, View-Consistent 3D Editing, BAGS, GeoGaussian, GS-Pose, Analytic-Splatting, Seamless 3D Maps, Texture-GS, Recent Advances in 3DGS, Compact 3DGS for Dense Visual SLAM, BrightDreamer, 3DGS-Reloc, Beyond Uncertainty, Motion-Aware 3DGS, Fed3DGS, GaussNav, 3DGS-Calib, and NEDS-SLAM
March 17, 2024:
- Update repo name and link for 3DGS.cpp (originally VulkanSplatting)
March 16, 2024:
- SplatTV
- Added 6 papers: GaussianGrasper, new splitting algorithm, Controllable Text-to-3D Generation, Spring-Mass 3DGS, Hyper-3DGS, and DreamScene
March 14, 2024:
- Added 6 papers: SemGauss, StyleGaussian, Gaussian Splatting in Style, GaussCtrl, GaussianImage, and RAIN-GS
March 8, 2024:
- Tutorial: Howto capture images for 3DGS
- Added 6 papers: SplattingAvatar, DNGaussian, Radiative Gaussians, BAGS, GSEdit, and ManiGaussian
March 8, 2024:
- Added 3DGStream Viewer
March 6, 2024:
- 1 paper added: Splat-Nav
March 5, 2024:
- 1 paper added: 3DGStream
- Code releases
- New viewer added
March 2, 2024:
- 1 paper added: 3D Gaussian Model for Animation and Texturing
- New section: Courses that also teach 3DGS.
February 28, 2024:
- VastGaussian
February 27, 2024:
- 2 papers added: Spec-Gaussian and GEA
- SC-GS code released
February 24, 2024:
- 2 papers added: Identifying unnecessary Gaussians and Gaussian Pro
February 23, 2024:
- Corrected Authors and updated abstract for EndoGS: Deformable Endoscopic Tissues Reconstruction with Gaussian Splatting
February 21, 2024:
- Added one paper: Reshaping SLAM: a Survey
February 20, 2024:
- GaussianObject code released
- Added one paper: GaussianHair
February 19, 2024:
- Blog post added: NeRFs vs. 3DGS.
February 16, 2024:
- 2 papers added: IM-3D and GES
- GaMeS code released
February 14, 2024:
- Added viewer: VulkanSplatting - cross-platform, high performance 3DGS renderer in C++ and Vulkan Compute
February 13, 2024:
- Code releases: (16th Jan 2024) Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting
- 3 papers added: 3DGala, ImplicitDeepFake, and 3D Gaussians as a New Vision Era.
February 9, 2024:
- 1 paper added: HeadStudio
February 8, 2024:
- 3 papers added: Rig3DGS, Mesh-based GS, and LGM
February 6, 2024: - Added 2 papers: SGS-SLAM and 4D Gaussian Splatting
February 5, 2024:
- Moved SWAGS to Dynmatics and Deformation section
- Added 2 paper: GaussianObject and GaMeSh
- GS++ renamed to Optimal Projection
February 2, 2024:
- Added 6 papers: VR-GS, Segment Anything, Gaussian Splashing, GS++, 360-GS, and StopThePop
- TRIPS code release
January 30, 2024:
- Code changes: GaussianAvatars code changed to private
January 29, 2024:
- Added 2 papers: LIV-GaussMap and TIP-Editor
January 26, 2024:
- Removed retracted paper: Animatable 3D Gaussians for High-fidelity Synthesis of Human Motions
- 3 papers added: EndoGaussians, PSAvatar, and GauU-Scene
January 25, 2024:
- Added viewer: Splatapult - 3d gaussian splatting renderer in C++ and OpenGL, works with OpenXR for tethered VR
January 24, 2024:
- Added utility: GSOPs (Gaussian Splat Operators) for SideFX Houdini
- Code releases: GaussianAvatars
January 23, 2024:
- 3 papers added: Amortized Gen3D, Deformable Endoscopic Tissues, Fast dynamic 3D Object Generation
- Code releases: Animatable Avatars, Compressed 3D Gaussians, GaussianAvatar
January 13, 2024:
- 4 papers added: CoSSegGaussians, TRIPS, Gaussian Shadow Casting for Neural Characters and DISTWAR
January 9, 2024:
- 1 paper added: A Survey on 3D Gaussian Splatting (The first survey)
January 8, 2024:
- 4 papers added: SWAGS (added paper from 2023 which I forgot to add before, ), first review paper, compressed 3DGS, and an application paper for Characterizing Satellite Geometry.
January 7, 2024:
- 1 Open source implementation: taichi-splatting - work is originally derived off Taichi 3D Gaussian Splatting, with significant re-organisation and changes.
January 5, 2024:
- 3 papers added: FMGS, PEGASUS, and Repaint123.
January 2, 2024:
- 1 paper added: Street Gaussians.
January 2, 2024:
- Deblurring Gaussians paper link updated.
- SAGA code released.
- 2 papers from 2023 added: Text2Immersion and 2D-Guided 3DG Segmentation.
- Mathematical supplemend of gsplat lib.
- Add years in categories.
- GSM code released.
December 29, 2023:
- 1 paper added (apparently missed that one before): Gaussian-Head-Avatar.
- Blog post head avatars added.
December 29, 2023:
- 3 papers added: DreamGaussian4D, 4DGen, and Spacetime Gaussian.
December 27, 2023:
- 3 papers added: LangSplat, Deformable 3DGS, and Human101.
- Blog post added: Comprehensive Review of 3DGS.
December 25, 2023:
- Efficient 3D Gaussian Representation for Monocular/Multi-view Dynamic Scenes code released.
- GPS-Gaussian code released.
December 24, 2023:
- 2 papers added: Self-Organization Gaussian Grids and Gaussian Splitting.
- Added repo for enhancing Gaussian rendering to model more complex scenes.
December 21, 2023:
- 3 papers added: Splatter Image, pixelSplat, and align your gaussians.
- Gaussian Grouping code released.
December 19, 2023:
- 2 papers added: GAvatar and GauFRe.
December 18, 2023:
- Added utility: SpectacularAI - Conversion scripts for different 3DGS conventions.
- SuGaR code released.
December 16, 2023:
- Added WebGL viewer 3: Gauzilla.
December 15, 2023:
- 4 papers added: DrivingGaussian, iComMa, Triplane, and 3DGS-Avatar.
- Relightable Gaussians code released.
December 13, 2023:
- 5 papers added: Gaussian-SLAM, CoGS, ASH, CF-GS, and Photo-SLAM.
December 11, 2023:
- 2 papers added: Gaussian Splatting SLAM and Denoising Scores for 3D Generation.
- ScaffoldGS code released.
December 8, 2023:
- 2 papers added: EAGLES and MonoGaussianAvatar.
December 7, 2023:
- LucidDreamer code released.
- 9 papers added: GauHuman, HeadGaS, HiFi4G, Gaussian-Flow, Feature-3DGS, Gaussian-Avatar, FlashAvatar, Relightable, and Deblurring Gaussians.
December 5, 2023:
- 9 papers added: NeuSG, GaussianHead, GaussianAvatars, GPS-Gaussian, Neural Parametric Gaussians for Monocular Non-Rigid Object Reconstruction, SplaTAM, MANUS, Segment Any, and Language embedded 3D Gaussians.
December 4, 2023:
- 8 papers added: Gaussian Grouping, MD Splatting, DynMF, Scaffold-GS, SparseGS, FSGS, Control4D, and SC-GS.
December 1, 2023:
- 4 papers added: Compact3D, GaussianShader, Periodic Vibration Gaussian and Gaussian Shell Maps for Efficient 3D Human Generation.
- Created Table of contents for each category and added line breaks.
November 30, 2023:
- Added Unreal game engine implementation.
- 5 papers added: LightGaussian, FisherRF, HUGS, HumanGaussian, CG3D, and Multi Scale 3DGS.
November 29, 2023:
- Added two papers: Point and Move and IR-GS.
November 28, 2023:
- Added five papers: GaussinEditor, Relightable Gaussians, GART, Mip-Splatting, HumanGaussian.
November 27, 2023:
- Added two papers: Gaussian Editing and Compact 3D Gaussians.
November 25, 2023:
- Animatable Gaussians project added (paper not yet released).
November 22, 2023:
- 3 new GS papers added: Animatable, Depth-Regularized, and Monocular/Multi-view 3DGS.
- Added some classic papers.
- Added another GS paper also called LucidDreamer.
November 21, 2023:
- 3 new GS papers added: GaussianDiffusion, LucidDreamer, PhysGaussian.
- 2 more GS papers added: SuGaR, PhysGaussian.
November 21, 2023:
- Added the paper GS-SLAM
November 17, 2023:
- Added PlayCanvas implementation to Game Engines section.
November 16, 2023:
- Deformable 3D Gaussians code released.
- Drivable 3D Gaussian Avatars paper added.
November 8, 2023:
- Some notes about the 3DGS implementation and unsive/rsal format discussion.
November 4, 2023:
- Added 2D gaussian splatting.
- Added very detailed (technical) blog post explaining 3D gaussian splatting.
October 28, 2023:
- Added Utilities Section.
- Added 3DGS Converter for editing 3DGS .ply files in Cloud Compare to Utilities.
- Added Kapture (for bundler to colmap model conversion) and Kapture image cropper script with conversion instructions to Utilities.
October 23, 2023:
- Added python WebGL viewer 2.
- Added Intro to gaussian splatting (and Unity viewer) video blog.
October 21, 2023:
- Added python OpenGL viewer.
- Added typescript WebGPU viewer.
October 20, 2023:
- Made abstracts readable (removed hyphenations).
- Added Windows tutorial.
- Other minor text fixes.
- Added Jupyter notebook viewer.
October 19, 2023:
- Added Github page link for Real-time Photorealistic Dynamic Scene Representation.
- Re-ordered headings.
- Added other unofficial implementations.
- Moved Nerfstudio gsplat and fast: C++/CUDA to Unofficial Implementations.
- Added Nerfstudio, Blender, WebRTC, iOS & Metal viewers.
October 17, 2023:
- GaussianDreamer code released.
- Added Real-time Photorealistic Dynamic Scene Representation.
October 16, 2023:
- Added Deformable 3D Gaussians paper.
- Dynamic 3D Gaussians code released.
October 15, 2023: Initial list with first 6 papers.
Seminal Paper introducing 3D Gaussian Splatting:
3D Gaussian Splatting for Real-Time Radiance Field Rendering
Authors: Bernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, George Drettakis
Abstract Radiance Field methods have recently revolutionized novel-view synthesis of scenes captured with multiple photos or videos. However, achieving high visual quality still requires neural networks that are costly to train and render, while recent faster methods inevitably trade off speed for quality. For unbounded and complete scenes (rather than isolated objects) and 1080p resolution rendering, no current method can achieve real-time display rates. We introduce three key elements that allow us to achieve state-of-the-art visual quality while maintaining competitive training times and importantly allow high-quality real-time (≥ 30 fps) novel-view synthesis at 1080p resolution. First, starting from sparse points produced during camera calibration, we represent the scene with 3D Gaussians that preserve desirable properties of continuous volumetric radiance fields for scene optimization while avoiding unnecessary computation in empty space; Second, we perform interleaved optimization/density control of the 3D Gaussians, notably optimizing anisotropic covariance to achieve an accurate representation of the scene; Third, we develop a fast visibility-aware rendering algorithm that supports anisotropic splatting and both accelerates training and allows real-time rendering. We demonstrate state-of-the-art visual quality and real-time rendering on several established datasets.📄 Paper (Low Resolution) | 📄 Paper (High Resolution) | 🌐 Project Page | 💻 Code | 🎥 Short Presentation | 🎥 Explanation Video
3D Object Detection:
2024:
1. 3DGS-DET: Empower 3D Gaussian Splatting with Boundary Guidance and Box-Focused Sampling for 3D Object Detection
Authors: Yang Cao, Yuanliang Jv, Dan Xu
Abstract Neural Radiance Fields (NeRF) are widely used for novel-view synthesis and have been adapted for 3D Object Detection (3DOD), offering a promising approach to 3D object detection through view-synthesis representation. However, NeRF faces inherent limitations: (i) It has limited representational capacity for 3DOD due to its implicit nature, and (ii) it suffers from slow rendering speeds. Recently, 3D Gaussian Splatting (3DGS) has emerged as an explicit 3D representation that addresses these limitations with faster rendering capabilities. Inspired by these advantages, this paper introduces 3DGS into 3DOD for the first time, identifying two main challenges: (i) Ambiguous spatial distribution of Gaussian blobs – 3DGS primarily relies on 2D pixel-level supervision, resulting in unclear 3D spatial distribution of Gaussian blobs and poor differentiation between objects and background, which hinders 3DOD; (ii) Excessive background blobs – 2D images often include numerous background pixels, leading to densely reconstructed 3DGS with many noisy Gaussian blobs representing the background, negatively affecting detection. To tackle the challenge (i), we leverage the fact that 3DGS reconstruction is derived from 2D images, and propose an elegant and efficient solution by incorporating 2D Boundary Guidance to significantly enhance the spatial distribution of Gaussian blobs, resulting in clearer differentiation between objects and their background (see Fig. 1). To address the challenge (ii), we propose a Box-Focused Sampling strategy using 2D boxes to generate object probability distribution in 3D spaces, allowing effective probabilistic sampling in 3D to retain more object blobs and reduce noisy background blobs. Benefiting from the proposed Boundary Guidance and Box-Focused Sampling, our final method, 3DGS-DET, achieves significant improvements (+5.6 on mAP@0.25, +3.7 on mAP@0.5) over our basic pipeline version, without introducing any additional learnable parameters. Furthermore, 3DGS-DET significantly outperforms the state-of-the-art NeRF-based method, NeRF-Det, achieving improvements of +6.6 on mAP@0.25 and +8.1 on mAP@0.5 for the ScanNet dataset, and impressive +31.5 on mAP@0.25 for the ARKITScenes dataset. Codes and models are publicly available at: https://github.com/yangcaoai/3DGS-DET.Autonomous Driving:
2024:
1. Street Gaussians for Modeling Dynamic Urban Scenes
Authors: Yunzhi Yan, Haotong Lin, Chenxu Zhou, Weijie Wang, Haiyang Sun, Kun Zhan, Xianpeng Lang, Xiaowei Zhou, Sida Peng
Abstract This paper aims to tackle the problem of modeling dynamic urban street scenes from monocular videos. Recent methods extend NeRF by incorporating tracked vehicle poses to animate vehicles, enabling photo-realistic view synthesis of dynamic urban street scenes. However, significant limitations are their slow training and rendering speed, coupled with the critical need for high precision in tracked vehicle poses. We introduce Street Gaussians, a new explicit scene representation that tackles all these limitations. Specifically, the dynamic urban street is represented as a set of point clouds equipped with semantic logits and 3D Gaussians, each associated with either a foreground vehicle or the background. To model the dynamics of foreground object vehicles, each object point cloud is optimized with optimizable tracked poses, along with a dynamic spherical harmonics model for the dynamic appearance. The explicit representation allows easy composition of object vehicles and background, which in turn allows for scene editing operations and rendering at 133 FPS (1066×1600 resolution) within half an hour of training. The proposed method is evaluated on multiple challenging benchmarks, including KITTI and Waymo Open datasets. Experiments show that the proposed method consistently outperforms state-of-the-art methods across all datasets. Furthermore, the proposed representation delivers performance on par with that achieved using precise ground-truth poses, despite relying only on poses from an off-the-shelf tracker.📄 Paper | 🌐 Project Page | 💻 Code (not yet)
2. TCLC-GS: Tightly Coupled LiDAR-Camera Gaussian Splatting for Surrounding Autonomous Driving Scenes
Authors: Cheng Zhao, Su Sun, Ruoyu Wang, Yuliang Guo, Jun-Jun Wan, Zhou Huang, Xinyu Huang, Yingjie Victor Chen, Liu Ren
Abstract Most 3D Gaussian Splatting (3D-GS) based methods for urban scenes initialize 3D Gaussians directly with 3D LiDAR points, which not only underutilizes LiDAR data capabilities but also overlooks the potential advantages of fusing LiDAR with camera data. In this paper, we design a novel tightly coupled LiDAR-Camera Gaussian Splatting (TCLC-GS) to fully leverage the combined strengths of both LiDAR and camera sensors, enabling rapid, high-quality 3D reconstruction and novel view RGB/depth synthesis. TCLC-GS designs a hybrid explicit (colorized 3D mesh) and implicit (hierarchical octree feature) 3D representation derived from LiDAR-camera data, to enrich the properties of 3D Gaussians for splatting. 3D Gaussian's properties are not only initialized in alignment with the 3D mesh which provides more completed 3D shape and color information, but are also endowed with broader contextual information through retrieved octree implicit features. During the Gaussian Splatting optimization process, the 3D mesh offers dense depth information as supervision, which enhances the training process by learning of a robust geometry. Comprehensive evaluations conducted on the Waymo Open Dataset and nuScenes Dataset validate our method's state-of-the-art (SOTA) performance. Utilizing a single NVIDIA RTX 3090 Ti, our method demonstrates fast training and achieves real-time RGB and depth rendering at 90 FPS in resolution of 1920x1280 (Waymo), and 120 FPS in resolution of 1600x900 (nuScenes) in urban scenarios.3. OmniRe: Omni Urban Scene Reconstruction
Authors: Ziyu Chen, Jiawei Yang, Jiahui Huang, Riccardo de Lutio, Janick Martinez Esturo, Boris Ivanovic, Or Litany, Zan Gojcic, Sanja Fidler, Marco Pavone, Li Song, Yue Wang
Abstract We introduce OmniRe, a holistic approach for efficiently reconstructing high-fidelity dynamic urban scenes from on-device logs. Recent methods for modeling driving sequences using neural radiance fields or Gaussian Splatting have demonstrated the potential of reconstructing challenging dynamic scenes, but often overlook pedestrians and other non-vehicle dynamic actors, hindering a complete pipeline for dynamic urban scene reconstruction. To that end, we propose a comprehensive 3DGS framework for driving scenes, named OmniRe, that allows for accurate, full-length reconstruction of diverse dynamic objects in a driving log. OmniRe builds dynamic neural scene graphs based on Gaussian representations and constructs multiple local canonical spaces that model various dynamic actors, including vehicles, pedestrians, and cyclists, among many others. This capability is unmatched by existing methods. OmniRe allows us to holistically reconstruct different objects present in the scene, subsequently enabling the simulation of reconstructed scenarios with all actors participating in real-time (~60Hz). Extensive evaluations on the Waymo dataset show that our approach outperforms prior state-of-the-art methods quantitatively and qualitatively by a large margin. We believe our work fills a critical gap in driving reconstruction.📄 Paper | 🌐 Project Page | 💻 Code
4. SplatAD: Real-Time Lidar and Camera Rendering with 3D Gaussian Splatting for Autonomous Driving
Authors: Georg Hess, Carl Lindström, Maryam Fatemi, Christoffer Petersson, Lennart Svensson
Abstract Ensuring the safety of autonomous robots, such as self-driving vehicles, requires extensive testing across diverse driving scenarios. Simulation is a key ingredient for conducting such testing in a cost-effective and scalable way. Neural rendering methods have gained popularity, as they can build simulation environments from collected logs in a data-driven manner. However, existing neural radiance field (NeRF) methods for sensor-realistic rendering of camera and lidar data suffer from low rendering speeds, limiting their applicability for large-scale testing. While 3D Gaussian Splatting (3DGS) enables real-time rendering, current methods are limited to camera data and are unable to render lidar data essential for autonomous driving. To address these limitations, we propose SplatAD, the first 3DGS-based method for realistic, real-time rendering of dynamic scenes for both camera and lidar data. SplatAD accurately models key sensor-specific phenomena such as rolling shutter effects, lidar intensity, and lidar ray dropouts, using purpose-built algorithms to optimize rendering efficiency. Evaluation across three autonomous driving datasets demonstrates that SplatAD achieves state-of-the-art rendering quality with up to +2 PSNR for NVS and +3 PSNR for reconstruction while increasing rendering speed over NeRF-based methods by an order of magnitude.📄 Paper | 🌐 Project Page | 💻 Code
2023:
1. [CVPR '24] DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenes
Authors: Xiaoyu Zhou, Zhiwei Lin, Xiaojun Shan, Yongtao Wang, Deqing Sun, Ming-Hsuan Yang
Abstract We present DrivingGaussian, an efficient and effective framework for surrounding dynamic autonomous driving scenes. For complex scenes with moving objects, we first sequentially and progressively model the static background of the entire scene with incremental static 3D Gaussians. We then leverage a composite dynamic Gaussian graph to handle multiple moving objects, individually reconstructing each object and restoring their accurate positions and occlusion relationships within the scene. We further use a LiDAR prior for Gaussian Splatting to reconstruct scenes with greater details and maintain panoramic consistency. DrivingGaussian outperforms existing methods in driving scene reconstruction and enables photorealistic surround-view synthesis with high-fidelity and multi-camera consistency.📄 Paper | 🌐 Project Page | 💻 Code (not yet)
2. [CVPR '24] HUGS: Holistic Urban 3D Scene Understanding via Gaussian Splatting
Authors: Hongyu Zhou, Jiahao Shao, Lu Xu, Dongfeng Bai, Weichao Qiu, Bingbing Liu, Yue Wang, Andreas Geiger, Yiyi Liao
Abstract Holistic understanding of urban scenes based on RGB images is a challenging yet important problem. It encompasses understanding both the geometry and appearance to enable novel view synthesis, parsing semantic labels, and tracking moving objects. Despite considerable progress, existing approaches often focus on specific aspects of this task and require additional inputs such as LiDAR scans or manually annotated 3D bounding boxes. In this paper, we introduce a novel pipeline that utilizes 3D Gaussian Splatting for holistic urban scene understanding. Our main idea involves the joint optimization of geometry, appearance, semantics, and motion using a combination of static and dynamic 3D Gaussians, where moving object poses are regularized via physical constraints. Our approach offers the ability to render new viewpoints in real-time, yielding 2D and 3D semantic information with high accuracy, and reconstruct dynamic scenes, even in scenarios where 3D bounding box detection are highly noisy. Experimental results on KITTI, KITTI-360, and Virtual KITTI 2 demonstrate the effectiveness of our approach.📄 Paper | 🌐 Project Page | 💻 Code
Avatars:
2024:
1. GaussianBody: Clothed Human Reconstruction via 3d Gaussian Splatting
Authors: Mengtian Li, Shengxiang Yao, Zhifeng Xie, Keyu Chen, Yu-Gang Jiang
Abstract In this work, we propose a novel clothed human reconstruction method called GaussianBody, based on 3D Gaussian Splatting. Compared with the costly neural radiance based models, 3D Gaussian Splatting has recently demonstrated great performance in terms of training time and rendering quality. However, applying the static 3D Gaussian Splatting model to the dynamic human reconstruction problem is non-trivial due to complicated non-rigid deformations and rich cloth details. To address these challenges, our method considers explicit pose-guided deformation to associate dynamic Gaussians across the canonical space and the observation space, introducing a physically-based prior with regularized transformations helps mitigate ambiguity between the two spaces. During the training process, we further propose a pose refinement strategy to update the pose regression for compensating the inaccurate initial estimation and a split-with-scale mechanism to enhance the density of regressed point clouds. The experiments validate that our method can achieve state-of-the-art photorealistic novel-view rendering results with high-quality details for dynamic clothed human bodies, along with explicit geometry reconstruction.2. PSAvatar: A Point-based Morphable Shape Model for Real-Time Head Avatar Creation with 3D Gaussian Splatting
Authors: Zhongyuan Zhao, Zhenyu Bao, Qing Li, Guoping Qiu, Kanglin Liu
Abstract Despite much progress, achieving real-time high-fidelity head avatar animation is still difficult and existing methods have to trade-off between speed and quality. 3DMM based methods often fail to model non-facial structures such as eyeglasses and hairstyles, while neural implicit models suffer from deformation inflexibility and rendering inefficiency. Although 3D Gaussian has been demonstrated to possess promising capability for geometry representation and radiance field reconstruction, applying 3D Gaussian in head avatar creation remains a major challenge since it is difficult for 3D Gaussian to model the head shape variations caused by changing poses and expressions. In this paper, we introduce PSAvatar, a novel framework for animatable head avatar creation that utilizes discrete geometric primitive to create a parametric morphable shape model and employs 3D Gaussian for fine detail representation and high fidelity rendering. The parametric morphable shape model is a Point-based Morphable Shape Model (PMSM) which uses points instead of meshes for 3D representation to achieve enhanced representation flexibility. The PMSM first converts the FLAME mesh to points by sampling on the surfaces as well as off the meshes to enable the reconstruction of not only surface-like structures but also complex geometries such as eyeglasses and hairstyles. By aligning these points with the head shape in an analysis-by-synthesis manner, the PMSM makes it possible to utilize 3D Gaussian for fine detail representation and appearance modeling, thus enabling the creation of high-fidelity avatars. We show that PSAvatar can reconstruct high-fidelity head avatars of a variety of subjects and the avatars can be animated in real-time (≥ 25 fps at a resolution of 512 × 512 ).3. Rig3DGS: Creating Controllable Portraits from Casual Monocular Videos
Authors: Alfredo Rivero, ShahRukh Athar, Zhixin Shu, Dimitris Samaras
Abstract Creating controllable 3D human portraits from casual smartphone videos is highly desirable due to their immense value in AR/VR applications. The recent development of 3D Gaussian Splatting (3DGS) has shown improvements in rendering quality and training efficiency. However, it still remains a challenge to accurately model and disentangle head movements and facial expressions from a single-view capture to achieve high-quality renderings. In this paper, we introduce Rig3DGS to address this challenge. We represent the entire scene, including the dynamic subject, using a set of 3D Gaussians in a canonical space. Using a set of control signals, such as head pose and expressions, we transform them to the 3D space with learned deformations to generate the desired rendering. Our key innovation is a carefully designed deformation method which is guided by a learnable prior derived from a 3D morphable model. This approach is highly efficient in training and effective in controlling facial expressions, head positions, and view synthesis across various captures. We demonstrate the effectiveness of our learned deformation through extensive quantitative and qualitative experiments.4. HeadStudio: Text to Animatable Head Avatars with 3D Gaussian Splatting
Authors: Zhenglin Zhou, Fan Ma, Hehe Fan, Yi Yang
Abstract Creating digital avatars from textual prompts has long been a desirable yet challenging task. Despite the promising outcomes obtained through 2D diffusion priors in recent works, current methods face challenges in achieving high-quality and animated avatars effectively. In this paper, we present HeadStudio, a novel framework that utilizes 3D Gaussian splatting to generate realistic and animated avatars from text prompts. Our method drives 3D Gaussians semantically to create a flexible and achievable appearance through the intermediate FLAME representation. Specifically, we incorporate the FLAME into both 3D representation and score distillation: 1) FLAME-based 3D Gaussian splatting, driving 3D Gaussian points by rigging each point to a FLAME mesh. 2) FLAME-based score distillation sampling, utilizing FLAME-based fine-grained control signal to guide score distillation from the text prompt. Extensive experiments demonstrate the efficacy of HeadStudio in generating animatable avatars from textual prompts, exhibiting visually appealing appearances. The avatars are capable of rendering high-quality real-time (≥40 fps) novel views at a resolution of 1024. They can be smoothly controlled by real-world speech and video. We hope that HeadStudio can advance digital avatar creation and that the present method can widely be applied across various domains.📄 Paper | 🌐 Project Page | 💻 Code (not yet)
5. ImplicitDeepfake: Plausible Face-Swapping through Implicit Deepfake Generation using NeRF and Gaussian Splatting
Authors: Georgii Stanishevskii, Jakub Steczkiewicz, Tomasz Szczepanik, Sławomir Tadeja, Jacek Tabor, Przemysław Spurek
Abstract Numerous emerging deep-learning techniques have had a substantial impact on computer graphics. Among the most promising breakthroughs are the recent rise of Neural Radiance Fields (NeRFs) and Gaussian Splatting (GS). NeRFs encode the object's shape and color in neural network weights using a handful of images with known camera positions to generate novel views. In contrast, GS provides accelerated training and inference without a decrease in rendering quality by encoding the object's characteristics in a collection of Gaussian distributions. These two techniques have found many use cases in spatial computing and other domains. On the other hand, the emergence of deepfake methods has sparked considerable controversy. Such techniques can have a form of artificial intelligence-generated videos that closely mimic authentic footage. Using generative models, they can modify facial features, enabling the creation of altered identities or facial expressions that exhibit a remarkably realistic appearance to a real person. Despite these controversies, deepfake can offer a next-generation solution for avatar creation and gaming when of desirable quality. To that end, we show how to combine all these emerging technologies to obtain a more plausible outcome. Our ImplicitDeepfake1 uses the classical deepfake algorithm to modify all training images separately and then train NeRF and GS on modified faces. Such relatively simple strategies can produce plausible 3D deepfake-based avatars.6. GaussianHair: Hair Modeling and Rendering with Light-aware Gaussians
Authors: Haimin Luo, Min Ouyang, Zijun Zhao, Suyi Jiang, Longwen Zhang, Qixuan Zhang, Wei Yang, Lan Xu, Jingyi Yu
Abstract Hairstyle reflects culture and ethnicity at first glance. In the digital era, various realistic human hairstyles are also critical to high-fidelity digital human assets for beauty and inclusivity. Yet, realistic hair modeling and real-time rendering for animation is a formidable challenge due to its sheer number of strands, complicated structures of geometry, and sophisticated interaction with light. This paper presents GaussianHair, a novel explicit hair representation. It enables comprehensive modeling of hair geometry and appearance from images, fostering innovative illumination effects and dynamic animation capabilities. At the heart of GaussianHair is the novel concept of representing each hair strand as a sequence of connected cylindrical 3D Gaussian primitives. This approach not only retains the hair's geometric structure and appearance but also allows for efficient rasterization onto a 2D image plane, facilitating differentiable volumetric rendering. We further enhance this model with the "GaussianHair Scattering Model", adept at recreating the slender structure of hair strands and accurately capturing their local diffuse color in uniform lighting. Through extensive experiments, we substantiate that GaussianHair achieves breakthroughs in both geometric and appearance fidelity, transcending the limitations encountered in state-of-the-art methods for hair reconstruction. Beyond representation, GaussianHair extends to support editing, relighting, and dynamic rendering of hair, offering seamless integration with conventional CG pipeline workflows. Complementing these advancements, we have compiled an extensive dataset of real human hair, each with meticulously detailed strand geometry, to propel further research in this field.7. GVA: Reconstructing Vivid 3D Gaussian Avatars from Monocular Videos
Authors: Xinqi Liu, Chenming Wu, Jialun Liu, Xing Liu, Jinbo Wu, Chen Zhao, Haocheng Feng, Errui Ding, Jingdong Wang
Abstract In this paper, we present a novel method that facilitates the creation of vivid 3D Gaussian avatars from monocular video inputs (GVA). Our innovation lies in addressing the intricate challenges of delivering high-fidelity human body reconstructions and aligning 3D Gaussians with human skin surfaces accurately. The key contributions of this paper are twofold. Firstly, we introduce a pose refinement technique to improve hand and foot pose accuracy by aligning normal maps and silhouettes. Precise pose is crucial for correct shape and appearance reconstruction. Secondly, we address the problems of unbalanced aggregation and initialization bias that previously diminished the quality of 3D Gaussian avatars, through a novel surface-guided re-initialization method that ensures accurate alignment of 3D Gaussian points with avatar surfaces. Experimental results demonstrate that our proposed method achieves high-fidelity and vivid 3D Gaussian avatar reconstruction. Extensive experimental analyses validate the performance qualitatively and quantitatively, demonstrating that it achieves state-of-the-art performance in photo-realistic novel view synthesis while offering fine-grained control over the human body and hand pose.📄 Paper | 🌐 Project Page | 💻 Code (not yet)
8. [CVPR '24] SplattingAvatar: Realistic Real-Time Human Avatars with Mesh-Embedded Gaussian Splatting
Authors: Zhijing Shao, Zhaolong Wang, Zhuang Li, Duotun Wang, Xiangru Lin, Yu Zhang, Mingming Fan, Zeyu Wang
Abstract We present SplattingAvatar, a hybrid 3D representation of photorealistic human avatars with Gaussian Splatting embedded on a triangle mesh, which renders over 300 FPS on a modern GPU and 30 FPS on a mobile device. We disentangle the motion and appearance of a virtual human with explicit mesh geometry and implicit appearance modeling with Gaussian Splatting. The Gaussians are defined by barycentric coordinates and displacement on a triangle mesh as Phong surfaces. We extend lifted optimization to simultaneously optimize the parameters of the Gaussians while walking on the triangle mesh. SplattingAvatar is a hybrid representation of virtual humans where the mesh represents low-frequency motion and surface deformation, while the Gaussians take over the high-frequency geometry and detailed appearance. Unlike existing deformation methods that rely on an MLP-based linear blend skinning (LBS) field for motion, we control the rotation and translation of the Gaussians directly by mesh, which empowers its compatibility with various animation techniques, e.g., skeletal animation, blend shapes, and mesh editing. Trainable from monocular videos for both full-body and head avatars, SplattingAvatar shows state-of-the-art rendering quality across multiple datasets.📄 Paper | 🌐 Project Page | 💻 Code| 🎥 Short Presentation
9. SplatFace: Gaussian Splat Face Reconstruction Leveraging an Optimizable Surface
Authors: Zhijing Shao, Zhaolong Wang, Zhuang Li, Duotun Wang, Xiangru Lin, Yu Zhang, Mingming Fan, Zeyu Wang
Abstract We present SplatFace, a novel Gaussian splatting framework designed for 3D human face reconstruction without reliance on accurate pre-determined geometry. Our method is designed to simultaneously deliver both high-quality novel view rendering and accurate 3D mesh reconstructions. We incorporate a generic 3D Morphable Model (3DMM) to provide a surface geometric structure, making it possible to reconstruct faces with a limited set of input images. We introduce a joint optimization strategy that refines both the Gaussians and the morphable surface through a synergistic non-rigid alignment process. A novel distance metric, splat-to-surface, is proposed to improve alignment by considering both the Gaussian position and covariance. The surface information is also utilized to incorporate a world-space densification process, resulting in superior reconstruction quality. Our experimental analysis demonstrates that the proposed method is competitive with both other Gaussian splatting techniques in novel view synthesis and other 3D reconstruction methods in producing 3D face meshes with high geometric precision.10. HAHA: Highly Articulated Gaussian Human Avatars with Textured Mesh Prior
Authors: Zhijing Shao, Zhaolong Wang, Zhuang Li, Duotun Wang, Xiangru Lin, Yu Zhang, Mingming Fan, Zeyu Wang
Abstract We present HAHA - a novel approach for animatable human avatar generation from monocular input videos. The proposed method relies on learning the trade-off between the use of Gaussian splatting and a textured mesh for efficient and high fidelity rendering. We demonstrate its efficiency to animate and render full-body human avatars controlled via the SMPL-X parametric model. Our model learns to apply Gaussian splatting only in areas of the SMPL-X mesh where it is necessary, like hair and out-of-mesh clothing. This results in a minimal number of Gaussians being used to represent the full avatar, and reduced rendering artifacts. This allows us to handle the animation of small body parts such as fingers that are traditionally disregarded. We demonstrate the effectiveness of our approach on two open datasets: SnapshotPeople and X-Humans. Our method demonstrates on par reconstruction quality to the state-of-the-art on SnapshotPeople, while using less than a third of Gaussians. HAHA outperforms previous state-of-the-art on novel poses from X-Humans both quantitatively and qualitatively.11. [CVPRW '24] Gaussian Splatting Decoder for 3D‑aware Generative Adversarial Networks
Authors: Florian Barthel, Arian Beckmann, Wieland Morgenstern, Anna Hilsmann, Peter Eisert
Abstract NeRF-based 3D-aware Generative Adversarial Networks like EG3D or GIRAFFE have shown very high rendering quality under large representational variety. However, rendering with Neural Radiance Fields poses several challenges for most 3D applications: First, the significant computational demands of NeRF rendering preclude its use on low-power devices, such as mobiles and VR/AR headsets. Second, implicit representations based on neural networks are difficult to incorporate into explicit 3D scenes, such as VR environments or video games. 3D Gaussian Splatting (3DGS) overcomes these limitations by providing an explicit 3D representation that can be rendered efficiently at high frame rates. In this work, we present a novel approach that combines the high rendering quality of NeRF-based 3D-aware Generative Adversarial Networks with the flexibility and computational advantages of 3DGS. By training a decoder that maps implicit NeRF representations to explicit 3D Gaussian Splatting attributes, we can integrate the representational diversity and quality of 3D GANs into the ecosystem of 3D Gaussian Splatting for the first time. Additionally, our approach allows for a high resolution GAN inversion and real-time GAN editing with 3D Gaussian Splatting scenes.📄 Paper | 🌐 Project Page | 💻 Code
12. GoMAvatar: Efficient Animatable Human Modeling from Monocular Video Using Gaussians-on-Mesh
Authors: Jing Wen, Xiaoming Zhao, Zhongzheng Ren, Alexander G. Schwing, Shenlong Wang
Abstract We introduce GoMAvatar, a novel approach for real-time, memory-efficient, high-quality animatable human modeling. GoMAvatar takes as input a single monocular video to create a digital avatar capable of re-articulation in new poses and real-time rendering from novel viewpoints, while seamlessly integrating with rasterization-based graphics pipelines. Central to our method is the Gaussians-on-Mesh representation, a hybrid 3D model combining rendering quality and speed of Gaussian splatting with geometry modeling and compatibility of deformable meshes. We assess GoMAvatar on ZJU-MoCap data and various YouTube videos. GoMAvatar matches or surpasses current monocular human modeling algorithms in rendering quality and significantly outperforms them in computational efficiency (43 FPS) while being memory-efficient (3.63 MB per subject).📄 Paper | 🌐 Project Page | 💻 Code
13. OccGaussian: 3D Gaussian Splatting for Occluded Human Rendering
Authors: Jingrui Ye, Zongkai Zhang, Yujiao Jiang, Qingmin Liao, Wenming Yang, Zongqing Lu
Abstract Rendering dynamic 3D human from monocular videos is crucial for various applications such as virtual reality and digital entertainment. Most methods assume the people is in an unobstructed scene, while various objects may cause the occlusion of body parts in real-life scenarios. Previous method utilizing NeRF for surface rendering to recover the occluded areas, but it requiring more than one day to train and several seconds to render, failing to meet the requirements of real-time interactive applications. To address these issues, we propose OccGaussian based on 3D Gaussian Splatting, which can be trained within 6 minutes and produces high-quality human renderings up to 160 FPS with occluded input. OccGaussian initializes 3D Gaussian distributions in the canonical space, and we perform occlusion feature query at occluded regions, the aggregated pixel-align feature is extracted to compensate for the missing information. Then we use Gaussian Feature MLP to further process the feature along with the occlusion-aware loss functions to better perceive the occluded area. Extensive experiments both in simulated and real-world occlusions, demonstrate that our method achieves comparable or even superior performance compared to the state-of-the-art method. And we improving training and inference speeds by 250x and 800x, respectively.14. [CVPR '24] Guess The Unseen: Dynamic 3D Scene Reconstruction from Partial 2D Glimpses
Authors: Inhee Lee, Byungjun Kim, Hanbyul Joo
Abstract In this paper, we present a method to reconstruct the world and multiple dynamic humans in 3D from a monocular video input. As a key idea, we represent both the world and multiple humans via the recently emerging 3D Gaussian Splatting (3D-GS) representation, enabling to conveniently and efficiently compose and render them together. In particular, we address the scenarios with severely limited and sparse observations in 3D human reconstruction, a common challenge encountered in the real world. To tackle this challenge, we introduce a novel approach to optimize the 3D-GS representation in a canonical space by fusing the sparse cues in the common space, where we leverage a pre-trained 2D diffusion model to synthesize unseen views while keeping the consistency with the observed 2D appearances. We demonstrate our method can reconstruct high-quality animatable 3D humans in various challenging examples, in the presence of occlusion, image crops, few-shot, and extremely sparse observations. After reconstruction, our method is capable of not only rendering the scene in any novel views at arbitrary time instances, but also editing the 3D scene by removing individual humans or applying different motions for each human. Through various experiments, we demonstrate the quality and efficiency of our methods over alternative existing approaches.📄 Paper | 🌐 Project Page | 💻 Code
15. [NeurIPS '24] Generalizable and Animatable Gaussian Head Avatar
Authors: Xuangeng Chu, Tatsuya Harada
Abstract In this paper, we propose Generalizable and Animatable Gaussian head Avatar (GAGAvatar) for one-shot animatable head avatar reconstruction. Existing methods rely on neural radiance fields, leading to heavy rendering consumption and low reenactment speeds. To address these limitations, we generate the parameters of 3D Gaussians from a single image in a single forward pass. The key innovation of our work is the proposed dual-lifting method, which produces high-fidelity 3D Gaussians that capture identity and facial details. Additionally, we leverage global image features and the 3D morphable model to construct 3D Gaussians for controlling expressions. After training, our model can reconstruct unseen identities without specific optimizations and perform reenactment rendering at real-time speeds. Experiments show that our method exhibits superior performance compared to previous methods in terms of reconstruction quality and expression accuracy. We believe our method can establish new benchmarks for future research and advance applications of digital avatars.📄 Paper | 🌐 Project Page | 💻 Code
16. [SIGGRAPH Asia '24] DualGS: Robust Dual Gaussian Splatting for Immersive Human-centric Volumetric Videos
Authors: Yuheng Jiang, Zhehao Shen, Yu Hong, Chengcheng Guo, Yize Wu, Yingliang Zhang, Jingyi Yu, Lan Xu
Abstract Volumetric video represents a transformative advancement in visual media, enabling users to freely navigate immersive virtual experiences and narrowing the gap between digital and real worlds. However, the need for extensive manual intervention to stabilize mesh sequences and the generation of excessively large assets in existing workflows impedes broader adoption. In this paper, we present a novel Gaussian-based approach, dubbed \textit{DualGS}, for real-time and high-fidelity playback of complex human performance with excellent compression ratios. Our key idea in DualGS is to separately represent motion and appearance using the corresponding skin and joint Gaussians. Such an explicit disentanglement can significantly reduce motion redundancy and enhance temporal coherence. We begin by initializing the DualGS and anchoring skin Gaussians to joint Gaussians at the first frame. Subsequently, we employ a coarse-to-fine training strategy for frame-by-frame human performance modeling. It includes a coarse alignment phase for overall motion prediction as well as a fine-grained optimization for robust tracking and high-fidelity rendering. To integrate volumetric video seamlessly into VR environments, we efficiently compress motion using entropy encoding and appearance using codec compression coupled with a persistent codebook. Our approach achieves a compression ratio of up to 120 times, only requiring approximately 350KB of storage per frame. We demonstrate the efficacy of our representation through photo-realistic, free-view experiences on VR headsets, enabling users to immersively watch musicians in performance and feel the rhythm of the notes at the performers' fingertips.📄 Paper | 🌐 Project Page | 🎥 Short Presentation | 💻 Dataset
17. [SIGGRAPH Asia '24] V^3: Viewing Volumetric Videos on Mobiles via Streamable 2D Dynamic Gaussians
Authors: Penghao Wang, Zhirui Zhang, Liao Wang, Kaixin Yao, Siyuan Xie, Jingyi Yu, Minye Wu, Lan Xu
Abstract Experiencing high-fidelity volumetric video as seamlessly as 2D videos is a long-held dream. However, current dynamic 3DGS methods, despite their high rendering quality, face challenges in streaming on mobile devices due to computational and bandwidth constraints. In this paper, we introduce V^3 (Viewing Volumetric Videos), a novel approach that enables high-quality mobile rendering through the streaming of dynamic Gaussians. Our key innovation is to view dynamic 3DGS as 2D videos, facilitating the use of hardware video codecs. Additionally, we propose a two-stage training strategy to reduce storage requirements with rapid training speed. The first stage employs hash encoding and shallow MLP to learn motion, then reduces the number of Gaussians through pruning to meet the streaming requirements, while the second stage fine tunes other Gaussian attributes using residual entropy loss and temporal loss to improve temporal continuity. This strategy, which disentangles motion and appearance, maintains high rendering quality with compact storage requirements. Meanwhile, we designed a multi-platform player to decode and render 2D Gaussian videos. Extensive experiments demonstrate the effectiveness of V^3, outperforming other methods by enabling high-quality rendering and streaming on common devices, which is unseen before. As the first to stream dynamic Gaussians on mobile devices, our companion player offers users an unprecedented volumetric video experience, including smooth scrolling and instant sharing. Our project page with source code is available at this https URL.📄 Paper | 🌐 Project Page | 🎥 Short Presentation
2023:
1. Drivable 3D Gaussian Avatars
Authors: Wojciech Zielonka, Timur Bagautdinov, Shunsuke Saito, Michael Zollhöfer, Justus Thies, Javier Romero
Abstract We present Drivable 3D Gaussian Avatars (D3GA), the first 3D controllable model for human bodies rendered with Gaussian splats. Current photorealistic drivable avatars require either accurate 3D registrations during training, dense input images during testing, or both. The ones based on neural radiance fields also tend to be prohibitively slow for telepresence applications. This work uses the recently presented 3D Gaussian Splatting (3DGS) technique to render realistic humans at real-time framerates, using dense calibrated multi-view videos as input. To deform those primitives, we depart from the commonly used point deformation method of linear blend skinning (LBS) and use a classic volumetric deformation method: cage deformations. Given their smaller size, we drive these deformations with joint angles and keypoints, which are more suitable for communication applications. Our experiments on nine subjects with varied body shapes, clothes, and motions obtain higher-quality results than state-of-the-art methods when using the same training and test data.📄 Paper | 🌐 Project Page | 🎥 Short Presentation
2. SplatArmor: Articulated Gaussian splatting for animatable humans from monocular RGB videos
Authors: Rohit Jena, Ganesh Subramanian Iyer, Siddharth Choudhary, Brandon Smith, Pratik Chaudhari, James Gee
Abstract We propose SplatArmor, a novel approach for recovering detailed and animatable human models by `armoring' a parameterized body model with 3D Gaussians. Our approach represents the human as a set of 3D Gaussians within a canonical space, whose articulation is defined by extending the skinning of the underlying SMPL geometry to arbitrary locations in the canonical space. To account for pose-dependent effects, we introduce a SE(3) field, which allows us to capture both the location and anisotropy of the Gaussians. Furthermore, we propose the use of a neural color field to provide color regularization and 3D supervision for the precise positioning of these Gaussians. We show that Gaussian splatting provides an interesting alternative to neural rendering based methods by leverging a rasterization primitive without facing any of the non-differentiability and optimization challenges typically faced in such approaches. The rasterization paradigms allows us to leverage forward skinning, and does not suffer from the ambiguities associated with inverse skinning and warping. We show compelling results on the ZJU MoCap and People Snapshot datasets, which underscore the effectiveness of our method for controllable human synthesis.📄 Paper | 🌐 Project Page | 💻 Code (not yet)
3. [CVPR '24] Animatable Gaussians: Learning Pose-dependent Gaussian Maps for High-fidelity Human Avatar Modeling
Authors: Zhe Li, Zerong Zheng, Lizhen Wang, Yebin Liu
Abstract Modeling animatable human avatars from RGB videos is a long-standing and challenging problem. Recent works usually adopt MLP-based neural radiance fields (NeRF) to represent 3D humans, but it remains difficult for pure MLPs to regress pose-dependent garment details. To this end, we introduce Animatable Gaussians, a new avatar representation that leverages powerful 2D CNNs and 3D Gaussian splatting to create high-fidelity avatars. To associate 3D Gaussians with the animatable avatar, we learn a parametric template from the input videos, and then parameterize the template on two front & back canonical Gaussian maps where each pixel represents a 3D Gaussian. The learned template is adaptive to the wearing garments for modeling looser clothes like dresses. Such template-guided 2D parameterization enables us to employ a powerful StyleGAN-based CNN to learn the pose-dependent Gaussian maps for modeling detailed dynamic appearances. Furthermore, we introduce a pose projection strategy for better generalization given novel poses. Overall, our method can create lifelike avatars with dynamic, realistic and generalized appearances. Experiments show that our method outperforms other state-of-the-art approaches.📄 Paper | 🌐 Project Page | 💻 Code
4. [CVPR '24] GART: Gaussian Articulated Template Models
Authors: Jiahui Lei, Yufu Wang, Georgios Pavlakos, Lingjie Liu, Kostas Daniilidis
Abstract We introduce Gaussian Articulated Template Model GART, an explicit, efficient, and expressive representation for non-rigid articulated subject capturing and rendering from monocular videos. GART utilizes a mixture of moving 3D Gaussians to explicitly approximate a deformable subject's geometry and appearance. It takes advantage of a categorical template model prior (SMPL, SMAL, etc.) with learnable forward skinning while further generalizing to more complex non-rigid deformations with novel latent bones. GART can be reconstructed via differentiable rendering from monocular videos in seconds or minutes and rendered in novel poses faster than 150fps.📄 Paper | 🌐 Project Page | 💻 Code | 🎥 Short Presentation
5. [CVPR '24] Human Gaussian Splatting: Real-time Rendering of Animatable Avatars
Authors: Arthur Moreau, Jifei Song, Helisa Dhamo, Richard Shaw, Yiren Zhou, Eduardo Pérez-Pellitero
Abstract This work addresses the problem of real-time rendering of photorealistic human body avatars learned from multi-view videos. While the classical approaches to model and render virtual humans generally use a textured mesh, recent research has developed neural body representations that achieve impressive visual quality. However, these models are difficult to render in real-time and their quality degrades when the character is animated with body poses different than the training observations. We propose an animatable human model based on 3D Gaussian Splatting, that has recently emerged as a very efficient alternative to neural radiance fields. The body is represented by a set of gaussian primitives in a canonical space which is deformed with a coarse to fine approach that combines forward skinning and local non-rigid refinement. We describe how to learn our Human Gaussian Splatting (HuGS) model in an end-to-end fashion from multi-view observations, and evaluate it against the state-of-the-art approaches for novel pose synthesis of clothed body. Our method achieves 1.5 dB PSNR improvement over the state-of-the-art on THuman4 dataset while being able to render in real-time (80 fps for 512x512 resolution).📄 Paper | 🌐 Project Page | 🎥 Short Presentation
6. [CVPR '24] HUGS: Human Gaussian Splats
Authors: Muhammed Kocabas, Jen-Hao Rick Chang, James Gabriel, Oncel Tuzel, Anurag Ranjan
Abstract Recent advances in neural rendering have improved both training and rendering times by orders of magnitude. While these methods demonstrate state-of-the-art quality and speed, they are designed for photogrammetry of static scenes and do not generalize well to freely moving humans in the environment. In this work, we introduce Human Gaussian Splats (HUGS) that represents an animatable human together with the scene using 3D Gaussian Splatting (3DGS). Our method takes only a monocular video with a small number of (50-100) frames, and it automatically learns to disentangle the static scene and a fully animatable human avatar within 30 minutes. We utilize the SMPL body model to initialize the human Gaussians. To capture details that are not modeled by SMPL (e.g. cloth, hairs), we allow the 3D Gaussians to deviate from the human body model. Utilizing 3D Gaussians for animated humans brings new challenges, including the artifacts created when articulating the Gaussians. We propose to jointly optimize the linear blend skinning weights to coordinate the movements of individual Gaussians during animation. Our approach enables novel-pose synthesis of human and novel view synthesis of both the human and the scene. We achieve state-of-the-art rendering quality with a rendering speed of 60 FPS while being ~100x faster to train over previous work.📄 Paper | 🌐 Project Page | 💻 Code (not yet)
7. [CVPR '24] Gaussian Shell Maps for Efficient 3D Human Generation
Authors: Rameen Abdal, Wang Yifan, Zifan Shi, Yinghao Xu, Ryan Po, Zhengfei Kuang, Qifeng Chen, Dit-Yan Yeung, Gordon Wetzstein
Abstract Efficient generation of 3D digital humans is important in several industries, including virtual reality, social media, and cinematic production. 3D generative adversarial networks (GANs) have demonstrated state-of-the-art (SOTA) quality and diversity for generated assets. Current 3D GAN architectures, however, typically rely on volume representations, which are slow to render, thereby hampering the GAN training and requiring multi-view-inconsistent 2D upsamplers. Here, we introduce Gaussian Shell Maps (GSMs) as a framework that connects SOTA generator network architectures with emerging 3D Gaussian rendering primitives using an articulable multi shell–based scaffold. In this setting, a CNN generates a 3D texture stack with features that are mapped to the shells. The latter represent inflated and deflated versions of a template surface of a digital human in a canonical body pose. Instead of rasterizing the shells directly, we sample 3D Gaussians on the shells whose attributes are encoded in the texture features. These Gaussians are efficiently and differentiably rendered. The ability to articulate the shells is important during GAN training and, at inference time, to deform a body into arbitrary userdefined poses. Our efficient rendering scheme bypasses the need for view-inconsistent upsamplers and achieves highquality multi-view consistent renderings at a native resolution of 512 × 512 pixels. We demonstrate that GSMs successfully generate 3D humans when trained on single-view datasets, including SHHQ and DeepFashion.📄 Paper | 🌐 Project Page | 💻 Code
8. GaussianHead: High-fidelity Head Avatars with Learnable Gaussian Derivation
Authors: Jie Wang, Jiu-Cheng Xie, Xianyan Li, Chi-Man Pun, Feng Xu, Hao Gao
Abstract Constructing vivid 3D head avatars for given subjects and realizing a series of animations on them is valuable yet challenging. This paper presents GaussianHead, which models the actional human head with anisotropic 3D Gaussians. In our framework, a motion deformation field and multi-resolution tri-plane are constructed respectively to deal with the head's dynamic geometry and complex texture. Notably, we impose an exclusive derivation scheme on each Gaussian, which generates its multiple doppelgangers through a set of learnable parameters for position transformation. With this design, we can compactly and accurately encode the appearance information of Gaussians, even those fitting the head's particular components with sophisticated structures. In addition, an inherited derivation strategy for newly added Gaussians is adopted to facilitate training acceleration. Extensive experiments show that our method can produce high-fidelity renderings, outperforming state-of-the-art approaches in reconstruction, cross-identity reenactment, and novel view synthesis tasks.📄 Paper | 🌐 Project Page | 💻 Code
9. [CVPR '24] GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians
Authors: Shenhan Qian, Tobias Kirschstein, Liam Schoneveld, Davide Davoli, Simon Giebenhain, Matthias Nießner
Abstract We introduce GaussianAvatars, a new method to create photorealistic head avatars that are fully controllable in terms of expression, pose, and viewpoint. The core idea is a dynamic 3D representation based on 3D Gaussian splats that are rigged to a parametric morphable face model. This combination facilitates photorealistic rendering while allowing for precise animation control via the underlying parametric model, e.g., through expression transfer from a driving sequence or by manually changing the morphable model parameters. We parameterize each splat by a local coordinate frame of a triangle and optimize for explicit displacement offset to obtain a more accurate geometric representation. During avatar reconstruction, we jointly optimize for the morphable model parameters and Gaussian splat parameters in an end-to-end fashion. We demonstrate the animation capabilities of our photorealistic avatar in several challenging scenarios. For instance, we show reenactments from a driving video, where our method outperforms existing works by a significant margin.📄 Paper | 🌐 Project Page | 💻 Code | 🎥 Short Presentation
10. [CVPR '24] GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesis
Authors: Shunyuan Zheng, Boyao Zhou, Ruizhi Shao, Boning Liu, Shengping Zhang, Liqiang Nie, Yebin Liu
Abstract We present a new approach, termed GPS-Gaussian, for synthesizing novel views of a character in a real-time manner. The proposed method enables 2K-resolution rendering under a sparse-view camera setting. Unlike the original Gaussian Splatting or neural implicit rendering methods that necessitate per-subject optimizations, we introduce Gaussian parameter maps defined on the source views and regress directly Gaussian Splatting properties for instant novel view synthesis without any fine-tuning or optimization. To this end, we train our Gaussian parameter regression module on a large amount of human scan data, jointly with a depth estimation module to lift 2D parameter maps to 3D space. The proposed framework is fully differentiable and experiments on several datasets demonstrate that our method outperforms state-of-the-art methods while achieving an exceeding rendering speed.📄 Paper | 🌐 Project Page | 💻 Code | 🎥 Short Presentation
11. GauHuman: Articulated Gaussian Splatting from Monocular Human Videos
Authors: Shoukang Hu Ziwei Liu
Abstract We present, GauHuman, a 3D human model with Gaussian Splatting for both fast training (1~2 minutes) and real-time rendering (up to 189 FPS), compared with existing NeRF-based implicit representation modelling frameworks demanding hours of training and seconds of rendering per frame. Specifically, GauHuman encodes Gaussian Splatting in the canonical space and transforms 3D Gaussians from canonical space to posed space with linear blend skinning (LBS), in which effective pose and LBS refinement modules are designed to learn fine details of 3D humans under negligible computational cost. Moreover, to enable fast optimization of GauHuman, we initialize and prune 3D Gaussians with 3D human prior, while splitting/cloning via KL divergence guidance, along with a novel merge operation for further speeding up. Extensive experiments on ZJU_Mocap and MonoCap datasets demonstrate that GauHuman achieves state-of-the-art performance quantitatively and qualitatively with fast training and real-time rendering speed. Notably, without sacrificing rendering quality, GauHuman can fast model the 3D human performer with ~13k 3D Gaussians.📄 Paper | 🌐 Project Page | 💻 Code | 🎥 Short Presentation
12. HeadGaS: Real-Time Animatable Head Avatars via 3D Gaussian Splatting
Authors: Helisa Dhamo, Yinyu Nie, Arthur Moreau, Jifei Song, Richard Shaw, Yiren Zhou, Eduardo Pérez-Pellitero
Abstract 3D head animation has seen major quality and runtime improvements over the last few years, particularly empowered by the advances in differentiable rendering and neural radiance fields. Real-time rendering is a highly desirable goal for real-world applications. We propose HeadGaS, the first model to use 3D Gaussian Splats (3DGS) for 3D head reconstruction and animation. In this paper we introduce a hybrid model that extends the explicit representation from 3DGS with a base of learnable latent features, which can be linearly blended with low-dimensional parameters from parametric head models to obtain expression-dependent final color and opacity values. We demonstrate that HeadGaS delivers state-of-the-art results in real-time inference frame rates, which surpasses baselines by up to ~2dB, while accelerating rendering speed by over x10.13. [CVPR '24] HiFi4G: High-Fidelity Human Performance Rendering via Compact Gaussian Splatting
Authors: Yuheng Jiang, Zhehao Shen, Penghao Wang, Zhuo Su, Yu Hong, Yingliang Zhang, Jingyi Yu, Lan Xu
Abstract We have recently seen tremendous progress in photo-real human modeling and rendering. Yet, efficiently rendering realistic human performance and integrating it into the rasterization pipeline remains challenging. In this paper, we present HiFi4G, an explicit and compact Gaussian-based approach for high-fidelity human performance rendering from dense footage. Our core intuition is to marry the 3D Gaussian representation with non-rigid tracking, achieving a compact and compression-friendly representation. We first propose a dual-graph mechanism to obtain motion priors, with a coarse deformation graph for effective initialization and a fine-grained Gaussian graph to enforce subsequent constraints. Then, we utilize a 4D Gaussian optimization scheme with adaptive spatial-temporal regularizers to effectively balance the non-rigid prior and Gaussian updating. We also present a companion compression scheme with residual compensation for immersive experiences on various platforms. It achieves a substantial compression rate of approximately 25 times, with less than 2MB of storage per frame. Extensive experiments demonstrate the effectiveness of our approach, which significantly outperforms existing approaches in terms of optimization speed, rendering quality, and storage overhead.📄 Paper | 🌐 Project Page | 🎥 Short Presentation | 💻 Dataset
14. [CVPR '24] GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D Gaussians
Authors: Liangxiao Hu, Hongwen Zhang, Yuxiang Zhang, Boyao Zhou, Boning Liu, Shengping Zhang, Liqiang Nie
Abstract We present GaussianAvatar, an efficient approach to creating realistic human avatars with dynamic 3D appearances from a single video. We start by introducing animatable 3D Gaussians to explicitly represent humans in various poses and clothing styles. Such an explicit and animatable representation can fuse 3D appearances more efficiently and consistently from 2D observations. Our representation is further augmented with dynamic properties to support pose-dependent appearance modeling, where a dynamic appearance network along with an optimizable feature tensor is designed to learn the motion-to-appearance mapping. Moreover, by leveraging the differentiable motion condition, our method enables a joint optimization of motions and appearances during avatar modeling, which helps to tackle the long-standing issue of inaccurate motion estimation in monocular settings. The efficacy of GaussianAvatar is validated on both the public dataset and our collected dataset, demonstrating its superior performances in terms of appearance quality and rendering efficiency.📄 Paper | 🌐 Project Page | 💻 Code | 🎥 Short Presentation
15. [CVPR '24] FlashAvatar: High-fidelity Head Avatar with Efficient Gaussian Embedding
Authors: Jun Xiang, Xuan Gao, Yudong Guo, Juyong Zhang
Abstract We propose FlashAvatar, a novel and lightweight 3D animatable avatar representation that could reconstruct a digital avatar from a short monocular video sequence in minutes and render high-fidelity photo-realistic images at 300FPS on a consumer-grade GPU. To achieve this, we maintain a uniform 3D Gaussian field embedded in the surface of a parametric face model and learn extra spatial offset to model non-surface regions and subtle facial details. While full use of geometric priors can capture high-frequency facial details and preserve exaggerated expressions, proper initialization can help reduce the number of Gaussians, thus enabling super-fast rendering speed. Extensive experimental results demonstrate that FlashAvatar outperforms existing works regarding visual quality and personalized details and is almost an order of magnitude faster in rendering speed.📄 Paper | 🌐 Project Page | 💻 Code
16. [CVPR '24] Relightable Gaussian Codec Avatars
Authors: Shunsuke Saito, Gabriel Schwartz, Tomas Simon, Junxuan Li, Giljoo Nam
Abstract The fidelity of relighting is bounded by both geometry and appearance representations. For geometry, both mesh and volumetric approaches have difficulty modeling intricate structures like 3D hair geometry. For appearance, existing relighting models are limited in fidelity and often too slow to render in real-time with high-resolution continuous environments. In this work, we present Relightable Gaussian Codec Avatars, a method to build high-fidelity relightable head avatars that can be animated to generate novel expressions. Our geometry model based on 3D Gaussians can capture 3D-consistent sub-millimeter details such as hair strands and pores on dynamic face sequences. To support diverse materials of human heads such as the eyes, skin, and hair in a unified manner, we present a novel relightable appearance model based on learnable radiance transfer. Together with global illumination-aware spherical harmonics for the diffuse components, we achieve real-time relighting with spatially all-frequency reflections using spherical Gaussians. This appearance model can be efficiently relit under both point light and continuous illumination. We further improve the fidelity of eye reflections and enable explicit gaze control by introducing relightable explicit eye models. Our method outperforms existing approaches without compromising real-time performance. We also demonstrate real-time relighting of avatars on a tethered consumer VR headset, showcasing the efficiency and fidelity of our avatars.17. MonoGaussianAvatar: Monocular Gaussian Point-based Head Avatar
Authors: Yufan Chen, Lizhen Wang, Qijing Li, Hongjiang Xiao, Shengping Zhang, Hongxun Yao, Yebin Liu
Abstract The ability to animate photo-realistic head avatars reconstructed from monocular portrait video sequences represents a crucial step in bridging the gap between the virtual and real worlds. Recent advancements in head avatar techniques, including explicit 3D morphable meshes (3DMM), point clouds, and neural implicit representation have been exploited for this ongoing research. However, 3DMM-based methods are constrained by their fixed topologies, point-based approaches suffer from a heavy training burden due to the extensive quantity of points involved, and the last ones suffer from limitations in deformation flexibility and rendering efficiency. In response to these challenges, we propose MonoGaussianAvatar (Monocular Gaussian Point-based Head Avatar), a novel approach that harnesses 3D Gaussian point representation coupled with a Gaussian deformation field to learn explicit head avatars from monocular portrait videos. We define our head avatars with Gaussian points characterized by adaptable shapes, enabling flexible topology. These points exhibit movement with a Gaussian deformation field in alignment with the target pose and expression of a person, facilitating efficient deformation. Additionally, the Gaussian points have controllable shape, size, color, and opacity combined with Gaussian splatting, allowing for efficient training and rendering. Experiments demonstrate the superior performance of our method, which achieves state-of-the-art results among previous methods.📄 Paper | 🌐 Project Page | 💻 Code (not yet) | 🎥 Short Presentation
18. [CVPR '24] ASH: Animatable Gaussian Splats for Efficient and Photoreal Human Rendering
Authors: Haokai Pang, Heming Zhu, Adam Kortylewski, Christian Theobalt, Marc Habermann
Abstract Real-time rendering of photorealistic and controllable human avatars stands as a cornerstone in Computer Vision and Graphics. While recent advances in neural implicit rendering have unlocked unprecedented photorealism for digital avatars, real-time performance has mostly been demonstrated for static scenes only. To address this, we propose ASH, an animatable Gaussian splatting approach for photorealistic rendering of dynamic humans in real-time. We parameterize the clothed human as animatable 3D Gaussians, which can be efficiently splatted into image space to generate the final rendering. However, naively learning the Gaussian parameters in 3D space poses a severe challenge in terms of compute. Instead, we attach the Gaussians onto a deformable character model, and learn their parameters in 2D texture space, which allows leveraging efficient 2D convolutional architectures that easily scale with the required number of Gaussians. We benchmark ASH with competing methods on pose-controllable avatars, demonstrating that our method outperforms existing real-time methods by a large margin and shows comparable or even better results than offline methods.📄 Paper | 🌐 Project Page | 💻 Code (not yet) | 🎥 Short Presentation
19. [CVPR '24] 3DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splatting
Authors: Zhiyin Qian, Shaofei Wang, Marko Mihajlovic, Andreas Geiger, Siyu Tang
Abstract We introduce an approach that creates animatable human avatars from monocular videos using 3D Gaussian Splatting (3DGS). Existing methods based on neural radiance fields (NeRFs) achieve high-quality novel-view/novel-pose image synthesis but often require days of training, and are extremely slow at inference time. Recently, the community has explored fast grid structures for efficient training of clothed avatars. Albeit being extremely fast at training, these methods can barely achieve an interactive rendering frame rate with around 15 FPS. In this paper, we use 3D Gaussian Splatting and learn a non-rigid deformation network to reconstruct animatable clothed human avatars that can be trained within 30 minutes and rendered at real-time frame rates (50+ FPS). Given the explicit nature of our representation, we further introduce as-isometric-as-possible regularizations on both the Gaussian mean vectors and the covariance matrices, enhancing the generalization of our model on highly articulated unseen poses. Experimental results show that our method achieves comparable and even better performance compared to state-of-the-art approaches on animatable avatar creation from a monocular input, while being 400x and 250x faster in training and inference, respectively.📄 Paper | 🌐 Project Page | 💻 Code | 🎥 Short Presentation
20. [CVPR '24] GAvatar: Animatable 3D Gaussian Avatars with Implicit Mesh Learning
Authors: Ye Yuan, Xueting Li, Yangyi Huang, Shalini De Mello, Koki Nagano, Jan Kautz, Umar Iqbal
Abstract Gaussian splatting has emerged as a powerful 3D representation that harnesses the advantages of both explicit (mesh) and implicit (NeRF) 3D representations. In this paper, we seek to leverage Gaussian splatting to generate realistic animatable avatars from textual descriptions, addressing the limitations (e.g., flexibility and efficiency) imposed by mesh or NeRF-based representations. However, a naive application of Gaussian splatting cannot generate high-quality animatable avatars and suffers from learning instability; it also cannot capture fine avatar geometries and often leads to degenerate body parts. To tackle these problems, we first propose a primitive-based 3D Gaussian representation where Gaussians are defined inside pose-driven primitives to facilitate animation. Second, to stabilize and amortize the learning of millions of Gaussians, we propose to use neural implicit fields to predict the Gaussian attributes (e.g., colors). Finally, to capture fine avatar geometries and extract detailed meshes, we propose a novel SDF-based implicit mesh learning approach for 3D Gaussians that regularizes the underlying geometries and extracts highly detailed textured meshes. Our proposed method, GAvatar, enables the large-scale generation of diverse animatable avatars using only text prompts. GAvatar significantly surpasses existing methods in terms of both appearance and geometry quality, and achieves extremely fast rendering (100 fps) at 1K resolution.📄 Paper | 🌐 Project Page | 🎥 Short Presentation
21. Deformable 3D Gaussian Splatting for Animatable Human Avatars
Authors: HyunJun Jung, Nikolas Brasch, Jifei Song, Eduardo Perez-Pellitero, Yiren Zhou, Zhihao Li, Nassir Navab, Benjamin Busam
Abstract Recent advances in neural radiance fields enable novel view synthesis of photo-realistic images in dynamic settings, which can be applied to scenarios with human animation. Commonly used implicit backbones to establish accurate models, however, require many input views and additional annotations such as human masks, UV maps and depth maps. In this work, we propose ParDy-Human (Parameterized Dynamic Human Avatar), a fully explicit approach to construct a digital avatar from as little as a single monocular sequence. ParDy-Human introduces parameter-driven dynamics into 3D Gaussian Splatting where 3D Gaussians are deformed by a human pose model to animate the avatar. Our method is composed of two parts: A first module that deforms canonical 3D Gaussians according to SMPL vertices and a consecutive module that further takes their designed joint encodings and predicts per Gaussian deformations to deal with dynamics beyond SMPL vertex deformations. Images are then synthesized by a rasterizer. ParDy-Human constitutes an explicit model for realistic dynamic human avatars which requires significantly fewer training views and images. Our avatars learning is free of additional annotations such as masks and can be trained with variable backgrounds while inferring full-resolution images efficiently even on consumer hardware. We provide experimental evidence to show that ParDy-Human outperforms state-of-the-art methods on ZJU-MoCap and THUman4.0 datasets both quantitatively and visually.22. Human101: Training 100+FPS Human Gaussians in 100s from 1 View
Authors: Mingwei Li, Jiachen Tao, Zongxin Yang, Yi Yang
Abstract Reconstructing the human body from single-view videos plays a pivotal role in the virtual reality domain. One prevalent application scenario necessitates the rapid reconstruction of high-fidelity 3D digital humans while simultaneously ensuring real-time rendering and interaction. Existing methods often struggle to fulfill both requirements. In this paper, we introduce Human101, a novel framework adept at producing high-fidelity dynamic 3D human reconstructions from 1-view videos by training 3D Gaussians in 100 seconds and rendering in 100+ FPS. Our method leverages the strengths of 3D Gaussian Splatting, which provides an explicit and efficient representation of 3D humans. Standing apart from prior NeRF-based pipelines, Human101 ingeniously applies a Human-centric Forward Gaussian Animation method to deform the parameters of 3D Gaussians, thereby enhancing rendering speed (i.e., rendering 1024-resolution images at an impressive 60+ FPS and rendering 512-resolution images at 100+ FPS). Experimental results indicate that our approach substantially eclipses current methods, clocking up to a 10 times surge in frames per second and delivering comparable or superior rendering quality.📄 Paper | 🌐 Project Page | 💻 Code (not yet)
23. [CVPR '24] Gaussian Head Avatar: Ultra High-fidelity Head Avatar via Dynamic Gaussians
Authors: Yuelang Xu, Benwang Chen, Zhe Li, Hongwen Zhang, Lizhen Wang, Zerong Zheng, Yebin Liu
Abstract Creating high-fidelity 3D head avatars has always been a research hotspot, but there remains a great challenge under lightweight sparse view setups. In this paper, we propose Gaussian Head Avatar represented by controllable 3D Gaussians for high-fidelity head avatar modeling. We optimize the neutral 3D Gaussians and a fully learned MLP-based deformation field to capture complex expressions. The two parts benefit each other, thereby our method can model fine-grained dynamic details while ensuring expression accuracy. Furthermore, we devise a well-designed geometry-guided initialization strategy based on implicit SDF and Deep Marching Tetrahedra for the stability and convergence of the training procedure. Experiments show our approach outperforms other state-of-the-art sparse-view methods, achieving ultra high-fidelity rendering quality at 2K resolution even under exaggerated expressions.📄 Paper | 🌐 Project Page | | 💻 Code | 🎥 Short Presentation
24. HumanSplat: Generalizable Single-Image Human Gaussian Splatting with Structure Priors
Authors: Panwang Pan, Zhuo Su, Chenguo Lin, Zhen Fan, Yongjie Zhang, Zeming Li, Tingting Shen, Yadong Mu, Yebin Liu
Abstract Despite recent advancements in high-fidelity human reconstruction techniques, the requirements for densely captured images or time-consuming per-instance optimization significantly hinder their applications in broader scenarios. To tackle these issues, we present HumanSplat that predicts the 3D Gaussian Splatting properties of any human from a single input image in a generalizable manner. In particular, HumanSplat comprises a 2D multi-view diffusion model and a latent reconstruction transformer with human structure priors that adeptly integrate geometric priors and semantic features within a unified framework. A hierarchical loss that incorporates human semantic information is further designed to achieve high-fidelity texture modeling and better constrain the estimated multiple views. Comprehensive experiments on standard benchmarks and in-the-wild images demonstrate that HumanSplat surpasses existing state-of-the-art methods in achieving photorealistic novel-view synthesis. Project page: https://humansplat.github.io/.Classic work:
1. A Generalization of Algebraic Surface Drawing
Authors: James F. Blinn
Comment:: First paper rendering 3D gaussians.
Abstract The mathematical description of three-dimensional surfaces usually falls into one of two classifications: parametric and implicit. An implicit surface is defined to be all points which satisfy some equation F (x, y, z) = 0. This form is ideally suited for image space shaded picture drawing; the pixel coordinates are substituted for x and y, and the equation is solved for z. Algorithms for drawing such objects have been developed primarily for first- and second-order polynomial functions, a subcategory known as algebraic surfaces. This paper presents a new algorithm applicable to other functional forms, in particular to the summation of several Gaussian density distributions. The algorithm was created to model electron density maps of molecular structures, but it can be used for other artistically interesting shapes.2. Approximate Differentiable Rendering with Algebraic Surfaces
Authors: Leonid Keselman and Martial Hebert
Comment:: First paper to do differentiable rendering optimization of 3D gaussians.
Abstract Differentiable renderers provide a direct mathematical link between an object’s 3D representation and images of that object. In this work, we develop an approximate differentiable renderer for a compact, interpretable representation, which we call Fuzzy Metaballs. Our approximate renderer focuses on rendering shapes via depth maps and silhouettes. It sacrifices fidelity for utility, producing fast runtimes and high-quality gradient information that can be used to solve vision tasks. Compared to mesh-based differentiable renderers, our method has forward passes that are 5x faster and backwards passes that are 30x faster. The depth maps and silhouette images generated by our method are smooth and defined everywhere. In our evaluation of differentiable renderers for pose estimation, we show that our method is the only one comparable to classic techniques. In shape from silhouette, our method performs well using only gradient descent and a per-pixel loss, without any surrogate losses or regularization. These reconstructions work well even on natural video sequences with segmentation artifacts.📄 Paper | 🌐 Project Page | 💻 Code | 🎥 Short Presentation
3. Unbiased Gradient Estimation for Differentiable Surface Splatting via Poisson Sampling
Authors: Jan U. Müller, Michael Weinmann, Reinhard Klein
Comment: Builds 2D screen-space gaussians from underlying 3D representations.
Abstract We propose an efficient and GPU-accelerated sampling framework which enables unbiased gradient approximation for differentiable point cloud rendering based on surface splatting. Our framework models the contribution of a point to the rendered image as a probability distribution. We derive an unbiased approximative gradient for the rendering function within this model. To efficiently evaluate the proposed sample estimate, we introduce a tree-based data-structure which employs multi-pole methods to draw samples in near linear time. Our gradient estimator allows us to avoid regularization required by previous methods, leading to a more faithful shape recovery from images. Furthermore, we validate that these improvements are applicable to real-world applications by refining the camera poses and point cloud obtained from a real-time SLAM system. Finally, employing our framework in a neural rendering setting optimizes both the point cloud and network parameters, highlighting the framework’s ability to enhance data driven approaches.4. Generating and Real-Time Rendering of Clouds
Authors: Petr Man
Comment: Splatting of anisotropic gaussians. Basically a non-differentiable implementation of 3DGS.
Abstract This paper presents a method for generation and real-time rendering of static clouds. Perlin noise function generates three dimensional map of a cloud. We also present a twopass rendering algorithm that performs physically based approximation. In the first preprocessed phase it computes multiple forward scattering. In the second phase first order anisotropic scattering at runtime is evaluated. The generated map is stored as voxels and is unsuitable for the real-time rendering. We introduce a more suitable inner representation of cloud that approximates the original map and contains much less information. The cloud is then represented by a set of metaballs (spheres) with parameters such as center positions, radii and density values. The main contribution of this paper is to propose a method, that transforms the original cloud map to the inner representation. This method uses the Radial Basis Function (RBF) neural network.Compression:
2024:
1. [I3D '24] Reducing the Memory Footprint of 3D Gaussian Splatting
Authors: Panagiotis Papantonakis, Georgios Kopanas, Bernhard Kerbl, Alexandre Lanvin, George Drettakis
Abstract 3D Gaussian splatting provides excellent visual quality for novel view synthesis, with fast training and realtime rendering; unfortunately, the memory requirements of this method for storing and transmission are unreasonably high. We first analyze the reasons for this, identifying three main areas where storage can be reduced: the number of 3D Gaussian primitives used to represent a scene, the number of coefficients for the spherical harmonics used to represent directional radiance, and the precision required to store Gaussian primitive attributes. We present a solution to each of these issues. First, we propose an efficient, resolutionaware primitive pruning approach, reducing the primitive count by half. Second, we introduce an adaptive adjustment method to choose the number of coefficients used to represent directional radiance for each Gaussian primitive, and finally a codebook-based quantization method, together with a half-float representation for further memory reduction. Taken together, these three components result in a ×27 reduction in overall size on disk on the standard datasets we tested, along with a x1.7 speedup in rendering speed. We demonstrate our method on standard datasets and show how our solution results in significantly reduced download times when using the method on a mobile device (see Fig. 1).📄 Paper | 🌐 Project Page | 💻 Code
2. [CVPR '24] Compressed 3D Gaussian Splatting for Accelerated Novel View Synthesis
Authors: Simon Niedermayr, Josef Stumpfegger, Rüdiger Westermann
Abstract Recently, high-fidelity scene reconstruction with an optimized 3D Gaussian splat representation has been introduced for novel view synthesis from sparse image sets. Making such representations suitable for applications like network streaming and rendering on low-power devices requires significantly reduced memory consumption as well as improved rendering efficiency. We propose a compressed 3D Gaussian splat representation that utilizes sensitivity-aware vector clustering with quantization-aware training to compress directional colors and Gaussian parameters. The learned codebooks have low bitrates and achieve a compression rate of up to 31× on real-world scenes with only minimal degradation of visual quality. We demonstrate that the compressed splat representation can be efficiently rendered with hardware rasterization on lightweight GPUs at up to 4× higher framerates than reported via an optimized GPU compute pipeline. Extensive experiments across multiple datasets demonstrate the robustness and rendering speed of the proposed approach.📄 Paper | 🌐 Project Page | 💻 Code
3. HAC: Hash-grid Assisted Context for 3D Gaussian Splatting Compression
Authors: Yihang Chen, Qianyi Wu, Jianfei Cai, Mehrtash Harandi, Weiyao Lin
Abstract 3D Gaussian Splatting (3DGS) has emerged as a promising framework for novel view synthesis, boasting rapid rendering speed with high fidelity. However, the substantial Gaussians and their associated attributes necessitate effective compression techniques. Nevertheless, the sparse and unorganized nature of the point cloud of Gaussians (or anchors in our paper) presents challenges for compression. To address this, we make use of the relations between the unorganized anchors and the structured hash grid, leveraging their mutual information for context modeling, and propose a Hash-grid Assisted Context (HAC) framework for highly compact 3DGS representation. Our approach introduces a binary hash grid to establish continuous spatial consistencies, allowing us to unveil the inherent spatial relations of anchors through a carefully designed context model. To facilitate entropy coding, we utilize Gaussian distributions to accurately estimate the probability of each quantized attribute, where an adaptive quantization module is proposed to enable high-precision quantization of these attributes for improved fidelity restoration. Additionally, we incorporate an adaptive masking strategy to eliminate invalid Gaussians and anchors. Importantly, our work is the pioneer to explore context-based compression for 3DGS representation, resulting in a remarkable size reduction of over 75× compared to vanilla 3DGS, while simultaneously improving fidelity, and achieving over 11× size reduction over SOTA 3DGS compression approach Scaffold-GS.📄 Paper | 🌐 Project Page | 💻 Code
4. [ECCV '24] End-to-End Rate-Distortion Optimized 3D Gaussian Representation
Authors: Henan Wang, Hanxin Zhu, Tianyu He, Runsen Feng, Jiajun Deng, Jiang Bian, Zhibo Chen
Abstract 3D Gaussian Splatting (3DGS) has become an emerging technique with remarkable potential in 3D representation and image rendering. However, the substantial storage overhead of 3DGS significantly impedes its practical applications. In this work, we formulate the compact 3D Gaussian learning as an end-to-end Rate-Distortion Optimization (RDO) problem and propose RDO-Gaussian that can achieve flexible and continuous rate control. RDO-Gaussian addresses two main issues that exist in current schemes: 1) Different from prior endeavors that minimize the rate under the fixed distortion, we introduce dynamic pruning and entropy-constrained vector quantization (ECVQ) that optimize the rate and distortion at the same time. 2) Previous works treat the colors of each Gaussian equally, while we model the colors of different regions and materials with learnable numbers of parameters. We verify our method on both real and synthetic scenes, showcasing that RDO-Gaussian greatly reduces the size of 3D Gaussian over 40×, and surpasses existing methods in rate-distortion performance.📄 Paper | 🌐 Project Page | 💻 Code
5. 3DGS.zip: A survey on 3D Gaussian Splatting Compression Methods
Authors: Milena T. Bagdasarian, Paul Knoll, Florian Barthel, Anna Hilsmann, Peter Eisert, Wieland Morgenstern
Abstract We present a work-in-progress survey on 3D Gaussian Splatting compression methods, focusing on their statistical performance across various benchmarks. This survey aims to facilitate comparability by summarizing key statistics of different compression approaches in a tabulated format. The datasets evaluated include TanksAndTemples, MipNeRF360, DeepBlending, and SyntheticNeRF. For each method, we report the Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM), Learned Perceptual Image Patch Similarity (LPIPS), and the resultant size in megabytes (MB), as provided by the respective authors. This is an ongoing, open project, and we invite contributions from the research community as GitHub issues or pull requests. Please visit http://w-m.github.io/3dgs-compression-survey/ for more information and a sortable version of the table.6. LapisGS: Layered Progressive 3D Gaussian Splatting for Adaptive Streaming
Authors: Yuang Shi, Simone Gasparini, Géraldine Morin, Wei Tsang Ooi,
Abstract The rise of Extended Reality (XR) requires efficient streaming of 3D online worlds, challenging current 3DGS representations to adapt to bandwidth-constrained environments. We propose LapisGS, a layered 3DGS that supports adaptive streaming and progressive rendering. Our method constructs a layered structure for cumulative representation, incorporates dynamic opacity optimization to maintain visual fidelity, and utilizes occupancy maps to efficiently manage Gaussian splats. This proposed model offers a progressive representation supporting a continuous rendering quality adapted for bandwidth-aware streaming. Extensive experiments validate the effectiveness of our approach in balancing visual fidelity with the compactness of the model, with up to 50.71% improvement in SSIM, 286.53% improvement in LPIPS, and 318.41% reduction in model size, and shows its potential for bandwidth-adapted 3D streaming and rendering applications.7. Implicit Gaussian Splatting with Efficient Multi-Level Tri-Plane Representation
Authors: Minye Wu, Tinne Tuytelaars
Abstract Recent advancements in photo-realistic novel view synthesis have been significantly driven by Gaussian Splatting (3DGS). Nevertheless, the explicit nature of 3DGS data entails considerable storage requirements, highlighting a pressing need for more efficient data representations. To address this, we present Implicit Gaussian Splatting (IGS), an innovative hybrid model that integrates explicit point clouds with implicit feature embeddings through a multi-level tri-plane architecture. This architecture features 2D feature grids at various resolutions across different levels, facilitating continuous spatial domain representation and enhancing spatial correlations among Gaussian primitives. Building upon this foundation, we introduce a level-based progressive training scheme, which incorporates explicit spatial regularization. This method capitalizes on spatial correlations to enhance both the rendering quality and the compactness of the IGS representation. Furthermore, we propose a novel compression pipeline tailored for both point clouds and 2D feature grids, considering the entropy variations across different levels. Extensive experimental evaluations demonstrate that our algorithm can deliver high-quality rendering using only a few MBs, effectively balancing storage efficiency and rendering fidelity, and yielding results that are competitive with the state-of-the-art.2023:
1. LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS
Authors: Zhiwen Fan, Kevin Wang, Kairun Wen, Zehao Zhu, Dejia Xu, Zhangyang Wang
Abstract Recent advancements in real-time neural rendering using point-based techniques have paved the way for the widespread adoption of 3D representations. However, foundational approaches like 3D Gaussian Splatting come with a substantial storage overhead caused by growing the SfM points to millions, often demanding gigabyte-level disk space for a single unbounded scene, posing significant scalability challenges and hindering the splatting efficiency. To address this challenge, we introduce LightGaussian, a novel method designed to transform 3D Gaussians into a more efficient and compact format. Drawing inspiration from the concept of Network Pruning, LightGaussian identifies Gaussians that are insignificant in contributing to the scene reconstruction and adopts a pruning and recovery process, effectively reducing redundancy in Gaussian counts while preserving visual effects. Additionally, LightGaussian employs distillation and pseudo-view augmentation to distill spherical harmonics to a lower degree, allowing knowledge transfer to more compact representations while maintaining reflectance. Furthermore, we propose a hybrid scheme, VecTree Quantization, to quantize all attributes, resulting in lower bitwidth representations with minimal accuracy losses. In summary, LightGaussian achieves an averaged compression rate over 15x while boosting the FPS from 139 to 215, enabling an efficient representation of complex scenes on Mip-NeRF 360, Tank and Temple datasets.📄 Paper | 🌐 Project Page | 💻 Code | 🎥 Short Presentation
2. Compact3D: Compressing Gaussian Splat Radiance Field Models with Vector Quantization
Authors: KL Navaneet, Kossar Pourahmadi Meibodi, Soroush Abbasi Koohpayegani, Hamed Pirsiavash
Abstract 3D Gaussian Splatting is a new method for modeling and rendering 3D radiance fields that achieves much faster learning and rendering time compared to SOTA NeRF methods. However, it comes with a drawback in the much larger storage demand compared to NeRF methods since it needs to store the parameters for several 3D Gaussians. We notice that many Gaussians may share similar parameters, so we introduce a simple vector quantization method based on \kmeans algorithm to quantize the Gaussian parameters. Then, we store the small codebook along with the index of the code for each Gaussian. Moreover, we compress the indices further by sorting them and using a method similar to run-length encoding. We do extensive experiments on standard benchmarks as well as a new benchmark which is an order of magnitude larger than the standard benchmarks. We show that our simple yet effective method can reduce the storage cost for the original 3D Gaussian Splatting method by a factor of almost 20× with a very small drop in the quality of rendered images.3. [CVPR '24] Compact 3D Gaussian Representation for Radiance Field
Authors: Joo Chan Lee, Daniel Rho, Xiangyu Sun, Jong Hwan Ko, Eunbyung Park
Abstract Neural Radiance Fields (NeRFs) have demonstrated remarkable potential in capturing complex 3D scenes with high fidelity. However, one persistent challenge that hinders the widespread adoption of NeRFs is the computational bottleneck due to the volumetric rendering. On the other hand, 3D Gaussian splatting (3DGS) has recently emerged as an alternative representation that leverages a 3D Gaussisan-based representation and adopts the rasterization pipeline to render the images rather than volumetric rendering, achieving very fast rendering speed and promising image quality. However, a significant drawback arises as 3DGS entails a substantial number of 3D Gaussians to maintain the high fidelity of the rendered images, which requires a large amount of memory and storage. To address this critical issue, we place a specific emphasis on two key objectives: reducing the number of Gaussian points without sacrificing performance and compressing the Gaussian attributes, such as view-dependent color and covariance. To this end, we propose a learnable mask strategy that significantly reduces the number of Gaussians while preserving high performance. In addition, we propose a compact but effective representation of view-dependent color by employing a grid-based neural field rather than relying on spherical harmonics. Finally, we learn codebooks to compactly represent the geometric attributes of Gaussian by vector quantization. In our extensive experiments, we consistently show over 10× reduced storage and enhanced rendering speed, while maintaining the quality of the scene representation, compared to 3DGS. Our work provides a comprehensive framework for 3D scene representation, achieving high performance, fast training, compactness, and real-time rendering.📄 Paper | 🌐 Project Page | 💻 Code
4. [ECCV '24] Compact 3D Scene Representation via Self-Organizing Gaussian Grids
Authors: Wieland Morgenstern, Florian Barthel, Anna Hilsmann, Peter Eisert
Abstract 3D Gaussian Splatting has recently emerged as a highly promising technique for modeling of static 3D scenes. In contrast to Neural Radiance Fields, it utilizes efficient rasterization allowing for very fast rendering at high-quality. However, the storage size is significantly higher, which hinders practical deployment, e.g. on resource constrained devices. In this paper, we introduce a compact scene representation organizing the parameters of 3D Gaussian Splatting (3DGS) into a 2D grid with local homogeneity, ensuring a drastic reduction in storage requirements without compromising visual quality during rendering. Central to our idea is the explicit exploitation of perceptual redundancies present in natural scenes. In essence, the inherent nature of a scene allows for numerous permutations of Gaussian parameters to equivalently represent it. To this end, we propose a novel highly parallel algorithm that regularly arranges the high-dimensional Gaussian parameters into a 2D grid while preserving their neighborhood structure. During training, we further enforce local smoothness between the sorted parameters in the grid. The uncompressed Gaussians use the same structure as 3DGS, ensuring a seamless integration with established renderers. Our method achieves a reduction factor of 17x to 42x in size for complex scenes with no increase in training time, marking a substantial leap forward in the domain of 3D scene distribution and consumption.📄 Paper | 🌐 Project Page | 💻 Code
Diffusion:
2024:
1. AGG: Amortized Generative 3D Gaussians for Single Image to 3D
Authors: Dejia Xu, Ye Yuan, Morteza Mardani, Sifei Liu, Jiaming Song, Zhangyang Wang, Arash Vahdat
Abstract Given the growing need for automatic 3D content creation pipelines, various 3D representations have been studied to generate 3D objects from a single image. Due to its superior rendering efficiency, 3D Gaussian splatting-based models have recently excelled in both 3D reconstruction and generation. 3D Gaussian splatting approaches for image to 3D generation are often optimization-based, requiring many computationally expensive score-distillation steps. To overcome these challenges, we introduce an Amortized Generative 3D Gaussian framework (AGG) that instantly produces 3D Gaussians from a single image, eliminating the need for per-instance optimization. Utilizing an intermediate hybrid representation, AGG decomposes the generation of 3D Gaussian locations and other appearance attributes for joint optimization. Moreover, we propose a cascaded pipeline that first generates a coarse representation of the 3D data and later upsamples it with a 3D Gaussian super-resolution module. Our method is evaluated against existing optimization-based 3D Gaussian frameworks and sampling-based pipelines utilizing other 3D representations, where AGG showcases competitive generation abilities both qualitatively and quantitatively while being several orders of magnitude faster.📄 Paper | 🌐 Project Page| 🎥 Short Presentation
2. Fast Dynamic 3D Object Generation from a Single-view Video
Authors: Zijie Pan, Zeyu Yang, Xiatian Zhu, Li Zhang
Abstract Generating dynamic three-dimensional (3D) object from a single-view video is challenging due to the lack of 4D labeled data. Existing methods extend text-to-3D pipelines by transferring off-the-shelf image generation models such as score distillation sampling, but they are slow and expensive to scale (e.g., 150 minutes per object) due to the need for back-propagating the information-limited supervision signals through a large pretrained model. To address this limitation, we propose an efficient video-to-4D object generation framework called Efficient4D. It generates high-quality spacetime-consistent images under different camera views, and then uses them as labeled data to directly train a novel 4D Gaussian splatting model with explicit point cloud geometry, enabling real-time rendering under continuous camera trajectories. Extensive experiments on synthetic and real videos show that Efficient4D offers a remarkable 10-fold increase in speed when compared to prior art alternatives while preserving the same level of innovative view synthesis quality. For example, Efficient4D takes only 14 minutes to model a dynamic object.📄 Paper | 🌐 Project Page | 💻 Code | 🎥 Short Presentation
3. GaussianObject: Just Taking Four Images to Get A High-Quality 3D Object with Gaussian Splatting
Authors: Chen Yang, Sikuang Li, Jiemin Fang, Ruofan Liang, Lingxi Xie, Xiaopeng Zhang, Wei Shen, Qi Tian
Abstract Reconstructing and rendering 3D objects from highly sparse views is of critical importance for promoting applications of 3D vision techniques and improving user experience. However, images from sparse views only contain very limited 3D information, leading to two significant challenges: 1) Difficulty in building multi-view consistency as images for matching are too few; 2) Partially omitted or highly compressed object information as view coverage is insufficient. To tackle these challenges, we propose GaussianObject, a framework to represent and render the 3D object with Gaussian splatting, that achieves high rendering quality with only 4 input images. We first introduce techniques of visual hull and floater elimination which explicitly inject structure priors into the initial optimization process for helping build multi-view consistency, yielding a coarse 3D Gaussian representation. Then we construct a Gaussian repair model based on diffusion models to supplement the omitted object information, where Gaussians are further refined. We design a self-generating strategy to obtain image pairs for training the repair model. Our GaussianObject is evaluated on several challenging datasets, including MipNeRF360, OmniObject3D, and OpenIllumination, achieving strong reconstruction results from only 4 views and significantly outperforming previous state-of-the-art methods.📄 Paper | 🌐 Project Page | 💻 Code | 🎥 Short Presentation
4.LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation
Authors: Chen Yang, Sikuang Li, Jiemin Fang, Ruofan Liang, Lingxi Xie, Xiaopeng Zhang, Wei Shen, Qi Tian
3D content creation has achieved significant progress in terms of both quality and speed. Although current feed-forward models can produce 3D objects in seconds, their resolution is constrained by the intensive computation required during training. In this paper, we introduce Large Multi-view Gaussian Model (LGM), a novel framework designed to generate high-resolution 3D models from text prompts or single-view images. Our key insights are two-fold: (1) 3D Representation: We propose multi-view Gaussian features as an efficient yet powerful representation, which can then be fused together for differentiable rendering. (2) 3D Backbone: We present an asymmetric U-Net as a high-throughput backbone operating on multi-view images, which can be produced from text or single-view image input by leveraging multi-view diffusion models. Extensive experiments demonstrate the high fidelity and efficiency of our approach. Notably, we maintain the fast speed to generate 3D objects within 5 seconds while boosting the training resolution to 512, thereby achieving high-resolution 3D content generation.📄 Paper | 🌐 Project Page | 💻 Code
5. GALA3D: Towards Text-to-3D Complex Scene Generation via Layout-guided Generative Gaussian Splatting
Authors: Xiaoyu Zhou, Xingjian Ran, Yajiao Xiong, Jinlin He, Zhiwei Lin, Yongtao Wang, Deqing Sun, Ming-Hsuan Yang
Abstract We present GALA3D, generative 3D GAussians with LAyout-guided control, for effective compositional text-to-3D generation. We first utilize large language models (LLMs) to generate the initial layout and introduce a layout-guided 3D Gaussian representation for 3D content generation with adaptive geometric constraints. We then propose an object-scene compositional optimization mechanism with conditioned diffusion to collaboratively generate realistic 3D scenes with consistent geometry, texture, scale, and accurate interactions among multiple objects while simultaneously adjusting the coarse layout priors extracted from the LLMs to align with the generated scene. Experiments show that GALA3D is a user-friendly, end-to-end framework for state-of-the-art scene-level 3D content generation and controllable editing while ensuring the high fidelity of object-level entities within the scene.📄 Paper | 🌐 Project Page | 💻 Code (not yet)
6. IM-3D: Iterative Multiview Diffusion and Reconstruction for High-Quality 3D Generation
Authors: Luke Melas-Kyriazi, Iro Laina, Christian Rupprecht, Natalia Neverova, Andrea Vedaldi, Oran Gafni, Filippos Kokkinos
Abstract Most text-to-3D generators build upon off-the-shelf text-to-image models trained on billions of images. They use variants of Score Distillation Sampling (SDS), which is slow, somewhat unstable, and prone to artifacts. A mitigation is to fine-tune the 2D generator to be multi-view aware, which can help distillation or can be combined with reconstruction networks to output 3D objects directly. In this paper, we further explore the design space of text-to-3D models. We significantly improve multi-view generation by considering video instead of image generators. Combined with a 3D reconstruction algorithm which, by using Gaussian splatting, can optimize a robust image-based loss, we directly produce high-quality 3D outputs from the generated views. Our new method, IM-3D, reduces the number of evaluations of the 2D generator network 10-100x, resulting in a much more efficient pipeline, better quality, fewer geometric inconsistencies, and higher yield of usable 3D assets.7. Controllable Text-to-3D Generation via Surface-Aligned Gaussian Splatting
Authors: Zhiqi Li, Yiming Chen, Lingzhe Zhao, Peidong Liu
Abstract While text-to-3D and image-to-3D generation tasks have received considerable attention, one important but under-explored field between them is controllable text-to-3D generation, which we mainly focus on in this work. To address this task, 1) we introduce ControlNet (MVControl), a novel neural network architecture designed to enhance existing pre-trained multi-view diffusion models by integrating additional input conditions, such as edge, depth, normal, and scribble maps. Our innovation lies in the introduction of a conditioning module that controls the base diffusion model using both local and global embeddings, which are computed from the input condition images and camera poses. Once trained, MVControl is able to offer 3D diffusion guidance for optimization-based 3D generation. And, 2) we propose an efficient multi-stage 3D generation pipeline that leverages the benefits of recent large reconstruction models and score distillation algorithm. Building upon our MVControl architecture, we employ a unique hybrid diffusion guidance method to direct the optimization process. In pursuit of efficiency, we adopt 3D Gaussians as our representation instead of the commonly used implicit representations. We also pioneer the use of SuGaR, a hybrid representation that binds Gaussians to mesh triangle faces. This approach alleviates the issue of poor geometry in 3D Gaussians and enables the direct sculpting of fine-grained geometry on the mesh. Extensive experiments demonstrate that our method achieves robust generalization and enables the controllable generation of high-quality 3D content.📄 Paper | 🌐 Project Page | 💻 Code
8. Hyper-3DG:Text-to-3D Gaussian Generation via Hypergraph
Authors: Donglin Di, Jiahui Yang, Chaofan Luo, Zhou Xue, Wei Chen, Xun Yang, Yue Gao
Abstract Text-to-3D generation represents an exciting field that has seen rapid advancements, facilitating the transformation of textual descriptions into detailed 3D models. However, current progress often neglects the intricate high-order correlation of geometry and texture within 3D objects, leading to challenges such as over-smoothness, over-saturation and the Janus problem. In this work, we propose a method named ``3D Gaussian Generation via Hypergraph (Hyper-3DG)'', designed to capture the sophisticated high-order correlations present within 3D objects. Our framework is anchored by a well-established mainflow and an essential module, named ``Geometry and Texture Hypergraph Refiner (HGRefiner)''. This module not only refines the representation of 3D Gaussians but also accelerates the update process of these 3D Gaussians by conducting the Patch-3DGS Hypergraph Learning on both explicit attributes and latent visual features. Our framework allows for the production of finely generated 3D objects within a cohesive optimization, effectively circumventing degradation. Extensive experimentation has shown that our proposed method significantly enhances the quality of 3D generation while incurring no additional computational overhead for the underlying framework.9. DreamScene: 3D Gaussian-based Text-to-3D Scene Generation via Formation Pattern Sampling
Authors: Haoran Li, Haolin Shi, Wenli Zhang, Wenjun Wu, Yong Liao, Lin Wang, Lik Hang Lee, Pengyuan Zhou
Abstract Text-to-3D scene generation holds immense potential for the gaming, film, and architecture sectors, increasingly capturing the attention of both academic and industry circles. Despite significant progress, current methods still struggle with maintaining high quality, consistency, and editing flexibility. In this paper, we propose DreamScene, a 3D Gaussian-based novel text-to-3D scene generation framework that leverages Formation Pattern Sampling (FPS) for core structuring, augmented with a strategic camera sampling and supported by holistic object-environment integration to overcome these hurdles. FPS, guided by the formation patterns of 3D objects, employs multi-timesteps sampling to quickly form semantically rich, high-quality representations, uses 3D Gaussian filtering for optimization stability, and leverages reconstruction techniques to generate plausible textures. The camera sampling strategy incorporates a progressive three-stage approach, specifically designed for both indoor and outdoor settings, to effectively ensure scene-wide 3D consistency. DreamScene enhances scene editing flexibility by combining objects and environments, enabling targeted adjustments. Extensive experiments showcase DreamScene's superiority over current state-of-the-art techniques, heralding its wide-ranging potential for diverse applications.📄 Paper | 🌐 Project Page | 💻 Code (not yet)
10. FDGaussian: Fast Gaussian Splatting from Single Image via Geometric-aware Diffusion Model
Authors: Qijun Feng, Zhen Xing, Zuxuan Wu, Yu-Gang Jiang
Abstract Reconstructing detailed 3D objects from single-view images remains a challenging task due to the limited information available. In this paper, we introduce FDGaussian, a novel two-stage framework for single-image 3D reconstruction. Recent methods typically utilize pre-trained 2D diffusion models to generate plausible novel views from the input image, yet they encounter issues with either multi-view inconsistency or lack of geometric fidelity. To overcome these challenges, we propose an orthogonal plane decomposition mechanism to extract 3D geometric features from the 2D input, enabling the generation of consistent multi-view images. Moreover, we further accelerate the state-of-the-art Gaussian Splatting incorporating epipolar attention to fuse images from different viewpoints. We demonstrate that FDGaussian generates images with high consistency across different views and reconstructs high-quality 3D objects, both qualitatively and quantitatively.11. BAGS: Building Animatable Gaussian Splatting from a Monocular Video with Diffusion Priors
Authors: Tingyang Zhang, Qingzhe Gao, Weiyu Li, Libin Liu, Baoquan Chen
Abstract Animatable 3D reconstruction has significant applications across various fields, primarily relying on artists' handcraft creation. Recently, some studies have successfully constructed animatable 3D models from monocular videos. However, these approaches require sufficient view coverage of the object within the input video and typically necessitate significant time and computational costs for training and rendering. This limitation restricts the practical applications. In this work, we propose a method to build animatable 3D Gaussian Splatting from monocular video with diffusion priors. The 3D Gaussian representations significantly accelerate the training and rendering process, and the diffusion priors allow the method to learn 3D models with limited viewpoints. We also present the rigid regularization to enhance the utilization of the priors. We perform an extensive evaluation across various real-world videos, demonstrating its superior performance compared to the current state-of-the-art methods.12. BrightDreamer: Generic 3D Gaussian Generative Framework for Fast Text-to-3D Synthesis
Authors: Lutao Jiang, Lin Wang
Abstract Text-to-3D synthesis has recently seen intriguing advances by combining the text-to-image models with 3D representation methods, e.g., Gaussian Splatting (GS), via Score Distillation Sampling (SDS). However, a hurdle of existing methods is the low efficiency, per-prompt optimization for a single 3D object. Therefore, it is imperative for a paradigm shift from per-prompt optimization to one-stage generation for any unseen text prompts, which yet remains challenging. A hurdle is how to directly generate a set of millions of 3D Gaussians to represent a 3D object. This paper presents BrightDreamer, an end-to-end single-stage approach that can achieve generalizable and fast (77 ms) text-to-3D generation. Our key idea is to formulate the generation process as estimating the 3D deformation from an anchor shape with predefined positions. For this, we first propose a Text-guided Shape Deformation (TSD) network to predict the deformed shape and its new positions, used as the centers (one attribute) of 3D Gaussians. To estimate the other four attributes (i.e., scaling, rotation, opacity, and SH coefficient), we then design a novel Text-guided Triplane Generator (TTG) to generate a triplane representation for a 3D object. The center of each Gaussian enables us to transform the triplane feature into the four attributes. The generated 3D Gaussians can be finally rendered at 705 frames per second. Extensive experiments demonstrate the superiority of our method over existing methods. Also, BrightDreamer possesses a strong semantic understanding capability even for complex text prompts.📄 Paper | 🌐 Project Page | 💻 Code
13. GVGEN: Text-to-3D Generation with Volumetric Representation
Authors: Xianglong He, Junyi Chen, Sida Peng, Di Huang, Yangguang Li, Xiaoshui Huang, Chun Yuan, Wanli Ouyang, Tong He
Abstract In recent years, 3D Gaussian splatting has emerged as a powerful technique for 3D reconstruction and generation, known for its fast and high-quality rendering capabilities. To address these shortcomings, this paper introduces a novel diffusion-based framework, GVGEN, designed to efficiently generate 3D Gaussian representations from text input. We propose two innovative techniques:(1) Structured Volumetric Representation. We first arrange disorganized 3D Gaussian points as a structured form GaussianVolume. This transformation allows the capture of intricate texture details within a volume composed of a fixed number of Gaussians. To better optimize the representation of these details, we propose a unique pruning and densifying method named the Candidate Pool Strategy, enhancing detail fidelity through selective optimization. (2) Coarse-to-fine Generation Pipeline. To simplify the generation of GaussianVolume and empower the model to generate instances with detailed 3D geometry, we propose a coarse-to-fine pipeline. It initially constructs a basic geometric structure, followed by the prediction of complete Gaussian attributes. Our framework, GVGEN, demonstrates superior performance in qualitative and quantitative assessments compared to existing 3D generation methods. Simultaneously, it maintains a fast generation speed (∼7 seconds), effectively striking a balance between quality and efficiency.📄 Paper | 🌐 Project Page | 💻 Code (not yet)
14. SyncTweedies: A General Generative Framework Based on Synchronized Diffusions
Authors: Jaihoon Kim, Juil Koo, Kyeongmin Yeo, Minhyuk Sung
Abstract We introduce a general framework for generating diverse visual content, including ambiguous images, panorama images, mesh textures, and Gaussian splat textures, by synchronizing multiple diffusion processes. We present exhaustive investigation into all possible scenarios for synchronizing multiple diffusion processes through a canonical space and analyze their characteristics across applications. In doing so, we reveal a previously unexplored case: averaging the outputs of Tweedie's formula while conducting denoising in multiple instance spaces. This case also provides the best quality with the widest applicability to downstream tasks. We name this case SyncTweedies. In our experiments generating visual content aforementioned, we demonstrate the superior quality of generation by SyncTweedies compared to other synchronization methods, optimization-based and iterative-update-based methods.📄 Paper | 🌐 Project Page | 💻 Code (not yet)
15. STAG4D: Spatial-Temporal Anchored Generative 4D Gaussians
Authors: Yifei Zeng, Yanqin Jiang, Siyu Zhu, Yuanxun Lu, Youtian Lin, Hao Zhu, Weiming Hu, Xun Cao, Yao Yao
Abstract Recent progress in pre-trained diffusion models and 3D generation have spurred interest in 4D content creation. However, achieving high-fidelity 4D generation with spatial-temporal consistency remains a challenge. In this work, we propose STAG4D, a novel framework that combines pre-trained diffusion models with dynamic 3D Gaussian splatting for high-fidelity 4D generation. Drawing inspiration from 3D generation techniques, we utilize a multi-view diffusion model to initialize multi-view images anchoring on the input video frames, where the video can be either real-world captured or generated by a video diffusion model. To ensure the temporal consistency of the multi-view sequence initialization, we introduce a simple yet effective fusion strategy to leverage the first frame as a temporal anchor in the self-attention computation. With the almost consistent multi-view sequences, we then apply the score distillation sampling to optimize the 4D Gaussian point cloud. The 4D Gaussian spatting is specially crafted for the generation task, where an adaptive densification strategy is proposed to mitigate the unstable Gaussian gradient for robust optimization. Notably, the proposed pipeline does not require any pre-training or fine-tuning of diffusion networks, offering a more accessible and practical solution for the 4D generation task. Extensive experiments demonstrate that our method outperforms prior 4D generation works in rendering quality, spatial-temporal consistency, and generation robustness, setting a new state-of-the-art for 4D generation from diverse inputs, including text, image, and video.📄 Paper | 🌐 Project Page | 💻 Code | 🎥 Short Presentation
16. Comp4D: LLM-Guided Compositional 4D Scene Generation
Authors: Dejia Xu, Hanwen Liang, Neel P. Bhatt, Hezhen Hu, Hanxue Liang, Konstantinos N. Plataniotis, Zhangyang Wang
Abstract Recent advancements in diffusion models for 2D and 3D content creation have sparked a surge of interest in generating 4D content. However, the scarcity of 3D scene datasets constrains current methodologies to primarily object-centric generation. To overcome this limitation, we present Comp4D, a novel framework for Compositional 4D Generation. Unlike conventional methods that generate a singular 4D representation of the entire scene, Comp4D innovatively constructs each 4D object within the scene separately. Utilizing Large Language Models (LLMs), the framework begins by decomposing an input text prompt into distinct entities and maps out their trajectories. It then constructs the compositional 4D scene by accurately positioning these objects along their designated paths. To refine the scene, our method employs a compositional score distillation technique guided by the pre-defined trajectories, utilizing pre-trained diffusion models across text-to-image, text-to-video, and text-to-3D domains. Extensive experiments demonstrate our outstanding 4D content creation capability compared to prior arts, showcasing superior visual quality, motion fidelity, and enhanced object interactions.📄 Paper | 🌐 Project Page | 💻 Code (not yet) | 🎥 Short Presentation
17. DreamPolisher: Towards High-Quality Text-to-3D Generation via Geometric Diffusion
Authors: Yuanze Lin, Ronald Clark, Philip Torr
Abstract We present DreamPolisher, a novel Gaussian Splatting based method with geometric guidance, tailored to learn cross-view consistency and intricate detail from textual descriptions. While recent progress on text-to-3D generation methods have been promising, prevailing methods often fail to ensure view-consistency and textural richness. This problem becomes particularly noticeable for methods that work with text input alone. To address this, we propose a two-stage Gaussian Splatting based approach that enforces geometric consistency among views. Initially, a coarse 3D generation undergoes refinement via geometric optimization. Subsequently, we use a ControlNet driven refiner coupled with the geometric consistency term to improve both texture fidelity and overall consistency of the generated 3D asset. Empirical evaluations across diverse textual prompts spanning various object categories demonstrate the efficacy of DreamPolisher in generating consistent and realistic 3D objects, aligning closely with the semantics of the textual instructions.📄 Paper | 🌐 Project Page | 💻 Code (not yet)
18. SC4D: Sparse-Controlled Video-to-4D Generation and Motion Transfer
Authors: Zijie Wu, Chaohui Yu, Yanqin Jiang, Chenjie Cao, Fan Wang, Xiang Bai
Abstract Recent advances in 2D/3D generative models enable the generation of dynamic 3D objects from a single-view video. Existing approaches utilize score distillation sampling to form the dynamic scene as dynamic NeRF or dense 3D Gaussians. However, these methods struggle to strike a balance among reference view alignment, spatio-temporal consistency, and motion fidelity under single-view conditions due to the implicit nature of NeRF or the intricate dense Gaussian motion prediction. To address these issues, this paper proposes an efficient, sparse-controlled video-to-4D framework named SC4D, that decouples motion and appearance to achieve superior video-to-4D generation. Moreover, we introduce Adaptive Gaussian (AG) initialization and Gaussian Alignment (GA) loss to mitigate shape degeneration issue, ensuring the fidelity of the learned motion and shape. Comprehensive experimental results demonstrate that our method surpasses existing methods in both quality and efficiency. In addition, facilitated by the disentangled modeling of motion and appearance of SC4D, we devise a novel application that seamlessly transfers the learned motion onto a diverse array of 4D entities according to textual descriptions.📄 Paper | 🌐 Project Page | 💻 Code (not yet) | 🎥 Short Presentation
19. Hash3D: Training-free Acceleration for 3D Generation
Authors: Xingyi Yang, Xinchao Wang
Abstract The evolution of 3D generative modeling has been notably propelled by the adoption of 2D diffusion models. Despite this progress, the cumbersome optimization process per se presents a critical hurdle to efficiency. In this paper, we introduce Hash3D, a universal acceleration for 3D generation without model training. Central to Hash3D is the insight that feature-map redundancy is prevalent in images rendered from camera positions and diffusion time-steps in close proximity. By effectively hashing and reusing these feature maps across neighboring timesteps and camera angles, Hash3D substantially prevents redundant calculations, thus accelerating the diffusion model's inference in 3D generation tasks. We achieve this through an adaptive grid-based hashing. Surprisingly, this feature-sharing mechanism not only speed up the generation but also enhances the smoothness and view consistency of the synthesized 3D objects. Our experiments covering 5 text-to-3D and 3 image-to-3D models, demonstrate Hash3D's versatility to speed up optimization, enhancing efficiency by 1.3 to 4 times. Additionally, Hash3D's integration with 3D Gaussian splatting largely speeds up 3D model creation, reducing text-to-3D processing to about 10 minutes and image-to-3D conversion to roughly 30 seconds.📄 Paper | 🌐 Project Page | 💻 Code
20. Zero-shot Point Cloud Completion Via 2D Priors
Authors: Tianxin Huang, Zhiwen Yan, Yuyang Zhao, Gim Hee Lee
Abstract 3D point cloud completion is designed to recover complete shapes from partially observed point clouds. Conventional completion methods typically depend on extensive point cloud data for training %, with their effectiveness often constrained to object categories similar to those seen during training. In contrast, we propose a zero-shot framework aimed at completing partially observed point clouds across any unseen categories. Leveraging point rendering via Gaussian Splatting, we develop techniques of Point Cloud Colorization and Zero-shot Fractal Completion that utilize 2D priors from pre-trained diffusion models to infer missing regions. Experimental results on both synthetic and real-world scanned point clouds demonstrate that our approach outperforms existing methods in completing a variety of objects without any requirement for specific training data.21. [ECCV '24] DreamScene360: Unconstrained Text-to-3D Scene Generation with Panoramic Gaussian Splatting
Authors: Shijie Zhou, Zhiwen Fan, Dejia Xu, Haoran Chang, Pradyumna Chari, Tejas Bharadwaj, Suya You, Zhangyang Wang, Achuta Kadambi
Abstract The increasing demand for virtual reality applications has highlighted the significance of crafting immersive 3D assets. We present a text-to-3D 360∘ scene generation pipeline that facilitates the creation of comprehensive 360∘ scenes for in-the-wild environments in a matter of minutes. Our approach utilizes the generative power of a 2D diffusion model and prompt self-refinement to create a high-quality and globally coherent panoramic image. This image acts as a preliminary "flat" (2D) scene representation. Subsequently, it is lifted into 3D Gaussians, employing splatting techniques to enable real-time exploration. To produce consistent 3D geometry, our pipeline constructs a spatially coherent structure by aligning the 2D monocular depth into a globally optimized point cloud. This point cloud serves as the initial state for the centroids of 3D Gaussians. In order to address invisible issues inherent in single-view inputs, we impose semantic and geometric constraints on both synthesized and input camera views as regularizations. These guide the optimization of Gaussians, aiding in the reconstruction of unseen regions. In summary, our method offers a globally consistent 3D scene within a 360∘ perspective, providing an enhanced immersive experience over existing techniques.📄 Paper | 🌐 Project Page | 💻 Code | 🎥 Short Presentation
22. RealmDreamer: Text-Driven 3D Scene Generation with Inpainting and Depth Diffusion
Authors: Jaidev Shriram, Alex Trevithick, Lingjie Liu, Ravi Ramamoorthi
Abstract We introduce RealmDreamer, a technique for generation of general forward-facing 3D scenes from text descriptions. Our technique optimizes a 3D Gaussian Splatting representation to match complex text prompts. We initialize these splats by utilizing the state-of-the-art text-to-image generators, lifting their samples into 3D, and computing the occlusion volume. We then optimize this representation across multiple views as a 3D inpainting task with image-conditional diffusion models. To learn correct geometric structure, we incorporate a depth diffusion model by conditioning on the samples from the inpainting model, giving rich geometric structure. Finally, we finetune the model using sharpened samples from image generators. Notably, our technique does not require video or multi-view data and can synthesize a variety of high-quality 3D scenes in different styles, consisting of multiple objects. Its generality additionally allows 3D synthesis from a single image📄 Paper | 🌐 Project Page | 💻 Code (not yet)
23. GaussianCube: A Structured and Explicit Radiance Representation for 3D Generative Modeling
Authors: Bowen Zhang, Yiji Cheng, Jiaolong Yang, Chunyu Wang, Feng Zhao, Yansong Tang, Dong Chen, Baining Guo
Abstract We introduce a radiance representation that is both structured and fully explicit and thus greatly facilitates 3D generative modeling. Existing radiance representations either require an implicit feature decoder, which significantly degrades the modeling power of the representation, or are spatially unstructured, making them difficult to integrate with mainstream 3D diffusion methods. We derive GaussianCube by first using a novel densification-constrained Gaussian fitting algorithm, which yields high-accuracy fitting using a fixed number of free Gaussians, and then rearranging these Gaussians into a predefined voxel grid via Optimal Transport. Since GaussianCube is a structured grid representation, it allows us to use standard 3D U-Net as our backbone in diffusion modeling without elaborate designs. More importantly, the high-accuracy fitting of the Gaussians allows us to achieve a high-quality representation with orders of magnitude fewer parameters than previous structured representations for comparable quality, ranging from one to two orders of magnitude. The compactness of GaussianCube greatly eases the difficulty of 3D generative modeling. Extensive experiments conducted on unconditional and class-conditioned object generation, digital avatar creation, and text-to-3D synthesis all show that our model achieves state-of-the-art generation results both qualitatively and quantitatively, underscoring the potential of GaussianCube as a highly accurate and versatile radiance representation for 3D generative modeling.📄 Paper | 🌐 Project Page | 💻 Code
24. 4Real: Towards Photorealistic 4D Scene Generation via Video Diffusion Models
Authors: Heng Yu, Chaoyang Wang, Peiye Zhuang, Willi Menapace, Aliaksandr Siarohin, Junli Cao, Laszlo A Jeni, Sergey Tulyakov, Hsin-Ying Lee
Abstract Existing dynamic scene generation methods mostly rely on distilling knowledge from pre-trained 3D generative models, which are typically fine-tuned on synthetic object datasets. As a result, the generated scenes are often object-centric and lack photorealism. To address these limitations, we introduce a novel pipeline designed for photorealistic text-to-4D scene generation, discarding the dependency on multi-view generative models and instead fully utilizing video generative models trained on diverse real-world datasets. Our method begins by generating a reference video using the video generation model. We then learn the canonical 3D representation of the video using a freeze-time video, delicately generated from the reference video. To handle inconsistencies in the freeze-time video, we jointly learn a per-frame deformation to model these imperfections. We then learn the temporal deformation based on the canonical representation to capture dynamic interactions in the reference video. The pipeline facilitates the generation of dynamic scenes with enhanced photorealism and structural integrity, viewable from multiple perspectives, thereby setting a new standard in 4D scene generation.📄 Paper | 🌐 Project Page | 💻 Code (not yet)
2023:
1. [CVPR '24] Text-to-3D using Gaussian Splatting
Authors: Zilong Chen, Feng Wang, Huaping Liu
Abstract In this paper, we present Gaussian Splatting based text-to-3D generation (GSGEN), a novel approach for generating high-quality 3D objects. Previous methods suffer from inaccurate geometry and limited fidelity due to the absence of 3D prior and proper representation. We leverage 3D Gaussian Splatting, a recent state-of-the-art representation, to address existing shortcomings by exploiting the explicit nature that enables the incorporation of 3D prior. Specifically, our method adopts a pro- gressive optimization strategy, which includes a geometry optimization stage and an appearance refinement stage. In geometry optimization, a coarse representation is established under a 3D geometry prior along with the ordinary 2D SDS loss, ensuring a sensible and 3D-consistent rough shape. Subsequently, the obtained Gaussians undergo an iterative refinement to enrich details. In this stage, we increase the number of Gaussians by compactness-based densification to enhance continuity and improve fidelity. With these designs, our approach can generate 3D content with delicate details and more accurate geometry. Extensive evaluations demonstrate the effectiveness of our method, especially for capturing high-frequency components.📄 Paper | 🌐 Project Page | 💻 Code | 🎥 Short Presentation | 🎥 Explanation Video
2. DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation
Authors: Jiaxiang Tang, Jiawei Ren, Hang Zhou, Ziwei Liu, Gang Zeng
Abstract Recent advances in 3D content creation mostly leverage optimization-based 3D generation via score distillation sampling (SDS). Though promising results have been exhibited, these methods often suffer from slow per-sample optimization, limiting their practical usage. In this paper, we propose DreamGaussian, a novel 3D content generation framework that achieves both efficiency and quality simultaneously. Our key insight is to design a generative 3D Gaussian Splatting model with companioned mesh extraction and texture refinement in UV space. In contrast to the occupancy pruning used in Neural Radiance Fields, we demonstrate that the progressive densification of 3D Gaussians converges significantly faster for 3D generative tasks. To further enhance the texture quality and facilitate downstream applications, we introduce an efficient algorithm to convert 3D Gaussians into textured meshes and apply a fine-tuning stage to refine the details. Extensive experiments demonstrate the superior efficiency and competitive generation quality of our proposed approach. Notably, DreamGaussian produces high-quality textured meshes in just 2 minutes from a single-view image, achieving approximately 10 times acceleration compared to existing methods.📄 Paper | 🌐 Project Page | 💻 Code | 🎥 Explanation Video
3. GaussianDreamer: Fast Generation from Text to 3D Gaussian Splatting with Point Cloud Priors
Authors: Taoran Yi1, Jiemin Fang, Guanjun Wu1, Lingxi Xie, Xiaopeng Zhang,
Wenyu Liu, Tian Qi, Xinggang Wang
📄 Paper | 🌐 Project Page | 💻 Code
4. GaussianDiffusion: 3D Gaussian Splatting for Denoising Diffusion Probabilistic Models with Structured Noise
Authors: Xinhai Li, Huaibin Wang, Kuo-Kun Tseng
Abstract Text-to-3D, known for its efficient generation methods and expansive creative potential, has garnered significant attention in the AIGC domain. However, the amalgamation of Nerf and 2D diffusion models frequently yields oversaturated images, posing severe limitations on downstream industrial applications due to the constraints of pixelwise rendering method. Gaussian splatting has recently superseded the traditional pointwise sampling technique prevalent in NeRF-based methodologies, revolutionizing various aspects of 3D reconstruction. This paper introduces a novel text to 3D content generation framework based on Gaussian splatting, enabling fine control over image saturation through individual Gaussian sphere transparencies, thereby producing more realistic images. The challenge of achieving multi-view consistency in 3D generation significantly impedes modeling complexity and accuracy. Taking inspiration from SJC, we explore employing multi-view noise distributions to perturb images generated by 3D Gaussian splatting, aiming to rectify inconsistencies in multi-view geometry. We ingeniously devise an efficient method to generate noise that produces Gaussian noise from diverse viewpoints, all originating from a shared noise source. Furthermore, vanilla 3D Gaussian-based generation tends to trap models in local minima, causing artifacts like floaters, burrs, or proliferative elements. To mitigate these issues, we propose the variational Gaussian splatting technique to enhance the quality and stability of 3D appearance. To our knowledge, our approach represents the first comprehensive utilization of Gaussian splatting across the entire spectrum of 3D content generation processes.5. [CVPR '24] LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matching
Authors: Yixun Liang, Xin Yang, Jiantao Lin, Haodong Li, Xiaogang Xu, Yingcong Chen
Abstract The recent advancements in text-to-3D generation mark a significant milestone in generative models, unlocking new possibilities for creating imaginative 3D assets across various real-world scenarios. While recent advancements in text-to-3D generation have shown promise, they often fall short in rendering detailed and high-quality 3D models. This problem is especially prevalent as many methods base themselves on Score Distillation Sampling (SDS). This paper identifies a notable deficiency in SDS, that it brings inconsistent and low-quality updating direction for the 3D model, causing the over-smoothing effect. To address this, we propose a novel approach called Interval Score Matching (ISM). ISM employs deterministic diffusing trajectories and utilizes interval-based score matching to counteract over-smoothing. Furthermore, we incorporate 3D Gaussian Splatting into our text-to-3D generation pipeline. Extensive experiments show that our model largely outperforms the state-of-the-art in quality and training efficiency.6. LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenes
Authors: Jaeyoung Chung, Suyoung Lee, Hyeongjin Nam, Jaerin Lee, Kyoung Mu Lee
Abstract With the widespread usage of VR devices and contents, demands for 3D scene generation techniques become more popular. Existing 3D scene generation models, however, limit the target scene to specific domain, primarily due to their training strategies using 3D scan dataset that is far from the real-world. To address such limitation, we propose LucidDreamer, a domain-free scene generation pipeline by fully leveraging the power of existing large-scale diffusion-based generative model. Our LucidDreamer has two alternate steps: Dreaming and Alignment. First, to generate multi-view consistent images from inputs, we set the point cloud as a geometrical guideline for each image generation. Specifically, we project a portion of point cloud to the desired view and provide the projection as a guidance for inpainting using the generative model. The inpainted images are lifted to 3D space with estimated depth maps, composing a new points. Second, to aggregate the new points into the 3D scene, we propose an aligning algorithm which harmoniously integrates the portions of newly generated 3D scenes. The finally obtained 3D scene serves as initial points for optimizing Gaussian splats. LucidDreamer produces Gaussian splats that are highly-detailed compared to the previous 3D scene generation methods, with no constraint on domain of the target scene.📄 Paper | 🌐 Project Page | 💻 Code
7. [CVPR '24] HumanGaussian: Text-Driven 3D Human Generation with Gaussian Splatting
Authors: Xian Liu, Xiaohang Zhan, Jiaxiang Tang, Ying Shan, Gang Zeng, Dahua Lin, Xihui Liu, Ziwei Liu
Abstract Realistic 3D human generation from text prompts is a desirable yet challenging task. Existing methods optimize 3D representations like mesh or neural fields via score distillation sampling (SDS), which suffers from inadequate fine details or excessive training time. In this paper, we propose an efficient yet effective framework, HumanGaussian, that generates high-quality 3D humans with fine-grained geometry and realistic appearance. Our key insight is that 3D Gaussian Splatting is an efficient renderer with periodic Gaussian shrinkage or growing, where such adaptive density control can be naturally guided by intrinsic human structures. Specifically, 1) we first propose a Structure-Aware SDS that simultaneously optimizes human appearance and geometry. The multi-modal score function from both RGB and depth space is leveraged to distill the Gaussian densification and pruning process. 2) Moreover, we devise an Annealed Negative Prompt Guidance by decomposing SDS into a noisier generative score and a cleaner classifier score, which well addresses the over-saturation issue. The floating artifacts are further eliminated based on Gaussian size in a prune-only phase to enhance generation smoothness. Extensive experiments demonstrate the superior efficiency and competitive quality of our framework, rendering vivid 3D humans under diverse scenarios.📄 Paper | 🌐 Project Page | 💻 Code | 🎥 Short Presentation
8. CG3D: Compositional Generation for Text-to-3D
Authors: Alexander Vilesov, Pradyumna Chari, Achuta Kadambi
Abstract With the onset of diffusion-based generative models and their ability to generate text-conditioned images, content generation has received a massive invigoration. Recently, these models have been shown to provide useful guidance for the generation of 3D graphics assets. However, existing work in text-conditioned 3D generation faces fundamental constraints: (i) inability to generate detailed, multi-object scenes, (ii) inability to textually control multi-object configurations, and (iii) physically realistic scene composition. In this work, we propose CG3D, a method for compositionally generating scalable 3D assets that resolves these constraints. We find that explicit Gaussian radiance fields, parameterized to allow for compositions of objects, possess the capability to enable semantically and physically consistent scenes. By utilizing a guidance framework built around this explicit representation, we show state of the art results, capable of even exceeding the guiding diffusion model in terms of object combinations and physics accuracy.📄 Paper | 🌐 Project Page | | 🎥 Short Presentation
9. Learn to Optimize Denoising Scores for 3D Generation - A Unified and Improved Diffusion Prior on NeRF and 3D Gaussian Splatting
Authors: Xiaofeng Yang, Yiwen Chen, Cheng Chen, Chi Zhang, Yi Xu, Xulei Yang, Fayao Liu and Guosheng Lin
Abstract We propose a unified framework aimed at enhancing the diffusion priors for 3D generation tasks. Despite the critical importance of these tasks, existing methodologies often struggle to generate high-caliber results. We begin by examining the inherent limitations in previous diffusion priors. We identify a divergence between the diffusion priors and the training procedures of diffusion models that substantially impairs the quality of 3D generation. To address this issue, we propose a novel, unified framework that iteratively optimizes both the 3D model and the diffusion prior. Leveraging the different learnable parameters of the diffusion prior, our approach offers multiple configurations, affording various trade-offs between performance and implementation complexity. Notably, our experimental results demonstrate that our method markedly surpasses existing techniques, establishing new state-of-the-art in the realm of text-to-3D generation. Furthermore, our approach exhibits impressive performance on both NeRF and the newly introduced 3D Gaussian Splatting backbones. Additionally, our framework yields insightful contributions to the understanding of recent score distillation methods, such as the VSD and DDS loss.📄 Paper | 🌐 Project Page | 💻 Code
10. [CVPR '24] Align Your Gaussians: Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion Models
Authors: Andreas Blattmann, Robin Rombach, Huan Ling, Tim Dockhorn, Seung Wook Kim, Sanja Fidler, Karsten Kreis
Abstract Recent advancements in 3D reconstruction from single images have been driven by the evolution of generative models. Prominent among these are methods based on Score Distillation Sampling (SDS) and the adaptation of diffusion models in the 3D domain. Despite their progress, these techniques often face limitations due to slow optimization or rendering processes, leading to extensive training and optimization times. In this paper, we introduce a novel approach for single-view reconstruction that efficiently generates a 3D model from a single image via feed-forward inference. Our method utilizes two transformer-based networks, namely a point decoder and a triplane decoder, to reconstruct 3D objects using a hybrid Triplane-Gaussian intermediate representation. This hybrid representation strikes a balance, achieving a faster rendering speed compared to implicit representations while simultaneously delivering superior rendering quality than explicit representations. The point decoder is designed for generating point clouds from single images, offering an explicit representation which is then utilized by the triplane decoder to query Gaussian features for each point. This design choice addresses the challenges associated with directly regressing explicit 3D Gaussian attributes characterized by their non-structural nature. Subsequently, the 3D Gaussians are decoded by an MLP to enable rapid rendering through splatting. Both decoders are built upon a scalable, transformer-based architecture and have been efficiently trained on large-scale 3D datasets. The evaluations conducted on both synthetic datasets and real-world images demonstrate that our method not only achieves higher quality but also ensures a faster runtime in comparison to previous state-of-the-art techniques.11. DreamGaussian4D: Generative 4D Gaussian Splatting
Authors: Jiawei Ren, Liang Pan, Jiaxiang Tang, Chi Zhang, Ang Cao, Gang Zeng, Ziwei Liu
Abstract Remarkable progress has been made in 4D content generation recently. However, existing methods suffer from long optimization time, lack of motion controllability, and a low level of detail. In this paper, we introduce DreamGaussian4D, an efficient 4D generation framework that builds on 4D Gaussian Splatting representation. Our key insight is that the explicit modeling of spatial transformations in Gaussian Splatting makes it more suitable for the 4D generation setting compared with implicit representations. DreamGaussian4D reduces the optimization time from several hours to just a few minutes, allows flexible control of the generated 3D motion, and produces animated meshes that can be efficiently rendered in 3D engines.📄 Paper | 🌐 Project Page | 💻 Code
12. 4DGen: Grounded 4D Content Generation with Spatial-temporal Consistency
Authors: Yuyang Yin, Dejia Xu, Zhangyang Wang, Yao Zhao, Yunchao Wei
Abstract Aided by text-to-image and text-to-video diffusion models, existing 4D content creation pipelines utilize score distillation sampling to optimize entire dynamic 3D scene. However, as these pipelines generate 4D content from text or image inputs, they incur significant time and effort in prompt engineering through trial and error. This work introduces 4DGen, a novel, holistic framework for grounded 4D content generation that decomposes the 4D generation task into multiple stages. We identify static 3D assets and monocular video sequences as key components in constructing the 4D content. Our pipeline facilitates conditional 4D generation, enabling users to specify geometry (3D assets) and motion (monocular videos), thus offering superior control over content creation. Furthermore, we construct our 4D representation using dynamic 3D Gaussians, which permits efficient, high-resolution supervision through rendering during training, thereby facilitating high-quality 4D generation. Additionally, we employ spatial-temporal pseudo labels on anchor frames, along with seamless consistency priors implemented through 3D-aware score distillation sampling and smoothness regularizations. Compared to existing baselines, our approach yields competitive results in faithfully reconstructing input signals and realistically inferring renderings from novel viewpoints and timesteps. Most importantly, our method supports grounded generation, offering users enhanced control, a feature difficult to achieve with previous methods.📄 Paper | 🌐 Project Page | 💻 Code | 🎥 Short Presentation
13. Text2Immersion: Generative Immersive Scene with 3D Gaussian
Authors: Hao Ouyang, Kathryn Heal, Stephen Lombardi, Tiancheng Sun
Abstract We introduce Text2Immersion, an elegant method for producing high-quality 3D immersive scenes from text prompts. Our proposed pipeline initiates by progressively generating a Gaussian cloud using pre-trained 2D diffusion and depth estimation models. This is followed by a refining stage on the Gaussian cloud, interpolating and refining it to enhance the details of the generated scene. Distinct from prevalent methods that focus on single object or indoor scenes, or employ zoom-out trajectories, our approach generates diverse scenes with various objects, even extending to the creation of imaginary scenes. Consequently, Text2Immersion can have wide-ranging implications for various applications such as virtual reality, game development, and automated content creation. Extensive evaluations demonstrate that our system surpasses other methods in rendering quality and diversity, further progressing towards text-driven 3D scene generation.📄 Paper | 🌐 Project Page | 💻 Code (not yet)
14. Repaint123: Fast and High-quality One Image to 3D Generation with Progressive Controllable 2D Repainting
Authors: Junwu Zhang, Zhenyu Tang, Yatian Pang, Xinhua Cheng, Peng Jin, Yida Wei, Munan Ning, Li Yuan
Abstract Recent one image to 3D generation methods commonly adopt Score Distillation Sampling (SDS). Despite the impressive results, there are multiple deficiencies including multi-view inconsistency, over-saturated and over-smoothed textures, as well as the slow generation speed. To address these deficiencies, we present Repaint123 to alleviate multi-view bias as well as texture degradation and speed up the generation process. The core idea is to combine the powerful image generation capability of the 2D diffusion model and the texture alignment ability of the repainting strategy for generating high-quality multi-view images with consistency. We further propose visibility-aware adaptive repainting strength for overlap regions to enhance the generated image quality in the repainting process. The generated high-quality and multi-view consistent images enable the use of simple Mean Square Error (MSE) loss for fast 3D content generation. We conduct extensive experiments and show that our method has a superior ability to generate high-quality 3D content with multi-view consistency and fine textures in 2 minutes from scratch.📄 Paper | 🌐 Project Page | 💻 Code (not yet)
Dynamics and Deformation:
2024:
1. 4D Gaussian Splatting: Towards Efficient Novel View Synthesis for Dynamic Scenes
Authors: Yuanxing Duan, Fangyin Wei, Qiyu Dai, Yuhang He, Wenzheng Chen, Baoquan Chen
Abstract We consider the problem of novel view synthesis (NVS) for dynamic scenes. Recent neural approaches have accomplished exceptional NVS results for static 3D scenes, but extensions to 4D time-varying scenes remain non-trivial. Prior efforts often encode dynamics by learning a canonical space plus implicit or explicit deformation fields, which struggle in challenging scenarios like sudden movements or capturing high-fidelity renderings. In this paper, we introduce 4D Gaussian Splatting (4DGS), a novel method that represents dynamic scenes with anisotropic 4D XYZT Gaussians, inspired by the success of 3D Gaussian Splatting in static scenes. We model dynamics at each timestamp by temporally slicing the 4D Gaussians, which naturally compose dynamic 3D Gaussians and can be seamlessly projected into images. As an explicit spatial-temporal representation, 4DGS demonstrates powerful capabilities for modeling complicated dynamics and fine details, especially for scenes with abrupt motions. We further implement our temporal slicing and splatting techniques in a highly optimized CUDA acceleration framework, achieving real-time inference rendering speeds of up to 277 FPS on an RTX 3090 GPU and 583 FPS on an RTX 4090 GPU. Rigorous evaluations on scenes with diverse motions showcase the superior efficiency and effectiveness of 4DGS, which consistently outperforms existing methods both quantitatively and qualitatively.2. GaussianFlow: Splatting Gaussian Dynamics for 4D Content Creation
Authors: Quankai Gao, Qiangeng Xu, Zhe Cao, Ben Mildenhall, Wenchao Ma, Le Chen, Danhang Tang, Ulrich Neumann
Abstract Creating 4D fields of Gaussian Splatting from images or videos is a challenging task due to its under-constrained nature. While the optimization can draw photometric reference from the input videos or be regulated by generative models, directly supervising Gaussian motions remains underexplored. In this paper, we introduce a novel concept, Gaussian flow, which connects the dynamics of 3D Gaussians and pixel velocities between consecutive frames. The Gaussian flow can be efficiently obtained by splatting Gaussian dynamics into the image space. This differentiable process enables direct dynamic supervision from optical flow. Our method significantly benefits 4D dynamic content generation and 4D novel view synthesis with Gaussian Splatting, especially for contents with rich motions that are hard to be handled by existing methods. The common color drifting issue that happens in 4D generation is also resolved with improved Guassian dynamics. Superior visual quality on extensive experiments demonstrates our method's effectiveness. Quantitative and qualitative evaluations show that our method achieves state-of-the-art results on both tasks of 4D generation and 4D novel view synthesis.📄 Paper | 🌐 Project Page | 💻 Code (not yet) | 🎥 Short Presentation
3. Motion-aware 3D Gaussian Splatting for Efficient Dynamic Scene Reconstruction
Authors: Zhiyang Guo, Wengang Zhou, Li Li, Min Wang, Houqiang Li
Abstract 3D Gaussian Splatting (3DGS) has become an emerging tool for dynamic scene reconstruction. However, existing methods focus mainly on extending static 3DGS into a time-variant representation, while overlooking the rich motion information carried by 2D observations, thus suffering from performance degradation and model redundancy. To address the above problem, we propose a novel motion-aware enhancement framework for dynamic scene reconstruction, which mines useful motion cues from optical flow to improve different paradigms of dynamic 3DGS. Specifically, we first establish a correspondence between 3D Gaussian movements and pixel-level flow. Then a novel flow augmentation method is introduced with additional insights into uncertainty and loss collaboration. Moreover, for the prevalent deformation-based paradigm that presents a harder optimization problem, a transient-aware deformation auxiliary module is proposed. We conduct extensive experiments on both multi-view and monocular scenes to verify the merits of our work. Compared with the baselines, our method shows significant superiority in both rendering quality and efficiency.4. Bridging 3D Gaussian and Mesh for Freeview Video Rendering
Authors: Yuting Xiao, Xuan Wang, Jiafei Li, Hongrui Cai, Yanbo Fan, Nan Xue, Minghui Yang, Yujun Shen, Shenghua Gao
Abstract This is only a preview version of GauMesh. Recently, primitive-based rendering has been proven to achieve convincing results in solving the problem of modeling and rendering the 3D dynamic scene from 2D images. Despite this, in the context of novel view synthesis, each type of primitive has its inherent defects in terms of representation ability. It is difficult to exploit the mesh to depict the fuzzy geometry. Meanwhile, the point-based splatting (e.g. the 3D Gaussian Splatting) method usually produces artifacts or blurry pixels in the area with smooth geometry and sharp textures. As a result, it is difficult, even not impossible, to represent the complex and dynamic scene with a single type of primitive. To this end, we propose a novel approach, GauMesh, to bridge the 3D Gaussian and Mesh for modeling and rendering the dynamic scenes. Given a sequence of tracked mesh as initialization, our goal is to simultaneously optimize the mesh geometry, color texture, opacity maps, a set of 3D Gaussians, and the deformation field. At a specific time, we perform α-blending on the RGB and opacity values based on the merged and re-ordered z-buffers from mesh and 3D Gaussian rasterizations. This produces the final rendering, which is supervised by the ground-truth image. Experiments demonstrate that our approach adapts the appropriate type of primitives to represent the different parts of the dynamic scene and outperforms all the baseline methods in both quantitative and qualitative comparisons without losing render speed.5. [ECCV '24] Per-Gaussian Embedding-Based Deformation for Deformable 3D Gaussian Splatting
Authors: Jeongmin Bae*, Seoha Kim*, Youngsik Yun, Hahyun Lee, Gun Bang, Youngjung Uh
Abstract As 3D Gaussian Splatting (3DGS) provides fast and high-quality novel view synthesis, it is a natural extension to deform a canonical 3DGS to multiple frames for representing a dynamic scene. However, previous works fail to accurately reconstruct complex dynamic scenes. We attribute the failure to the design of the deformation field, which is built as a coordinate-based function. This approach is problematic because 3DGS is a mixture of multiple fields centered at the Gaussians, not just a single coordinate-based framework. To resolve this problem, we define the deformation as a function of per-Gaussian embeddings and temporal embeddings. Moreover, we decompose deformations as coarse and fine deformations to model slow and fast movements, respectively. Also, we introduce a local smoothness regularization for per-Gaussian embedding to improve the details in dynamic regions.📄 Paper | 🌐 Project Page | 💻 Code
6. DreamScene4D: Dynamic Multi-Object Scene Generation from Monocular Videos
Authors: Wen-Hsuan Chu, Lei Ke, Katerina Fragkiadaki
Abstract Existing VLMs can track in-the-wild 2D video objects while current generative models provide powerful visual priors for synthesizing novel views for the highly under-constrained 2D-to-3D object lifting. Building upon this exciting progress, we present DreamScene4D, the first approach that can generate three-dimensional dynamic scenes of multiple objects from monocular in-the-wild videos with large object motion across occlusions and novel viewpoints. Our key insight is to design a "decompose-then-recompose" scheme to factorize both the whole video scene and each object's 3D motion. We first decompose the video scene by using open-vocabulary mask trackers and an adapted image diffusion model to segment, track, and amodally complete the objects and background in the video. Each object track is mapped to a set of 3D Gaussians that deform and move in space and time. We also factorize the observed motion into multiple components to handle fast motion. The camera motion can be inferred by re-rendering the background to match the video frames. For the object motion, we first model the object-centric deformation of the objects by leveraging rendering losses and multi-view generative priors in an object-centric frame, then optimize object-centric to world-frame transformations by comparing the rendered outputs against the perceived pixel and optical flow. Finally, we recompose the background and objects and optimize for relative object scales using monocular depth prediction guidance. We show extensive results on the challenging DAVIS, Kubric, and self-captured videos, detail some limitations, and provide future directions. Besides 4D scene generation, our results show that DreamScene4D enables accurate 2D point motion tracking by projecting the inferred 3D trajectories to 2D, while never explicitly trained to do so.📄 Paper | 🌐 Project Page | 💻 Code (not yet)
7. [CVPR '24] 3D Geometry-aware Deformable Gaussian Splatting for Dynamic View Synthesis
Authors: Zhicheng Lu, Xiang Guo, Le Hui, Tianrui Chen, Min Yang, Xiao Tang, Feng Zhu, Yuchao Dai
Abstract In this paper, we propose a 3D geometry-aware deformable Gaussian Splatting method for dynamic view synthesis. Existing neural radiance fields (NeRF) based solutions learn the deformation in an implicit manner, which cannot incorporate 3D scene geometry. Therefore, the learned deformation is not necessarily geometrically coherent, which results in unsatisfactory dynamic view synthesis and 3D dynamic reconstruction. Recently, 3D Gaussian Splatting provides a new representation of the 3D scene, building upon which the 3D geometry could be exploited in learning the complex 3D deformation. Specifically, the scenes are represented as a collection of 3D Gaussian, where each 3D Gaussian is optimized to move and rotate over time to model the deformation. To enforce the 3D scene geometry constraint during deformation, we explicitly extract 3D geometry features and integrate them in learning the 3D deformation. In this way, our solution achieves 3D geometry-aware deformation modeling, which enables improved dynamic view synthesis and 3D dynamic reconstruction. Extensive experimental results on both synthetic and real datasets prove the superiority of our solution, which achieves new state-of-the-art performance.📄 Paper | 🌐 Project Page | 💻 Code (not yet)
8. MoDGS: Dynamic Gaussian Splatting from Causually-captured Monocular Videos
Authors: Qingming Liu*, Yuan Liu*, Jiepeng Wang, Xianqiang Lv,Peng Wang, Wenping Wang, Junhui Hou†,
Abstract In this paper, we propose MoDGS, a new pipeline to render novel-view images in dynamic scenes using only casually captured monocular videos. Previous monocular dynamic NeRF or Gaussian Splatting methods strongly rely on the rapid movement of input cameras to construct multiview consistency but fail to reconstruct dynamic scenes on casually captured input videos whose cameras are static or move slowly.To address this challenging task, MoDGS adopts recent single-view depth estimation methods to guide the learning of the dynamic scene. Then, a novel 3D-aware initialization method is proposed to learn a reasonable deformation field and a new robust depth loss is proposed to guide the learning of dynamic scene geometry. Comprehensive experiments demonstrate that MoDGS is able to render high-quality novel view images of dynamic scenes from just a casually captured monocular video, which outperforms baseline methods by a significant margin.
📄 Paper | 🌐 Project Page | 💻 Code (not yet)
9. [ECCVW '24] Optimizing Dynamic NeRF and 3DGS with No Video Synchronization
Authors: Seoha Kim*, Jeongmin Bae*, Youngsik Yun, HyunSeung Son, Hahyun Lee, Gun Bang, Youngjung Uh
Abstract Recent advancements in 4D scene reconstruction using dynamic NeRF and 3DGS have demonstrated the ability to represent dynamic scenes from multi-view videos. However, they fail to reconstruct the dynamic scenes and struggle to fit even the training views in unsynchronized settings. It happens because they employ a single latent embedding for a frame, while the multi-view images at the same frame were actually captured at different moments. To address this limitation, we introduce time offsets for individual unsynchronized videos and jointly optimize the offsets with the field. By design, our method is applicable for various baselines, even regardless of the types of radiance fields. We conduct experiments on the common Plenoptic Video Dataset and a newly built Unsynchronized Dynamic Blender Dataset to verify the performance of our method.10. [NeurIPS '24] MotionGS: Exploring Explicit Motion Guidance for Deformable 3D Gaussian Splatting
Authors: Ruijie Zhu*, Yanzhe Liang*, Hanzhi Chang, Jiacheng Deng, Jiahao Lu, Wenfei Yang, Tianzhu Zhang, Yongdong Zhang
Abstract Dynamic scene reconstruction is a long-term challenge in the field of 3D vision. Recently, the emergence of 3D Gaussian Splatting has provided new insights into this problem. Although subsequent efforts rapidly extend static 3D Gaussian to dynamic scenes, they often lack explicit constraints on object motion, leading to optimization difficulties and performance degradation. To address the above issues, we propose a novel deformable 3D Gaussian splatting framework called MotionGS, which explores explicit motion priors to guide the deformation of 3D Gaussians. Specifically, we first introduce an optical flow decoupling module that decouples optical flow into camera flow and motion flow, corresponding to camera movement and object motion respectively. Then the motion flow can effectively constrain the deformation of 3D Gaussians, thus simulating the motion of dynamic objects. Additionally, a camera pose refinement module is proposed to alternately optimize 3D Gaussians and camera poses, mitigating the impact of inaccurate camera poses. Extensive experiments in the monocular dynamic scenes validate that MotionGS surpasses state-of-the-art methods and exhibits significant superiority in both qualitative and quantitative results.📄 Paper | 🌐 Project Page | 💻 Code (not yet)
11. [ECCV '24] DGD: Dynamic 3D Gaussians Distillation
Authors: Isaac Labe*, Noam Issachar*, Itai Lang, Sagie Benaim
Abstract We tackle the task of learning dynamic 3D semantic radiance fields given a single monocular video as input. Our learned semantic radiance field captures per-point semantics as well as color and geometric properties for a dynamic 3D scene, enabling the generation of novel views and their corresponding semantics. This enables the segmentation and tracking of a diverse set of 3D semantic entities, specified using a simple and intuitive interface that includes a user click or a text prompt. To this end, we present DGD, a unified 3D representation for both the appearance and semantics of a dynamic 3D scene, building upon the recently proposed dynamic 3D Gaussians representation. Our representation is optimized over time with both color and semantic information. Key to our method is the joint optimization of the appearance and semantic attributes, which jointly affect the geometric properties of the scene. We evaluate our approach in its ability to enable dense semantic 3D object tracking and demonstrate high-quality results that are fast to render, for a diverse set of scenes.📄 Paper | 🌐 Project Page | 💻 Code | 🎥 Short Presentation
12. [NeurIPS '24] Fully Explicit Dynamic Gaussian Splatting
Authors: Junoh Lee, Changyeon Won, HyunJun Jung, Inhwan Bae, Hae-Gon Jeon
Abstract 3D Gaussian Splatting has shown fast and high-quality rendering results in static scenes by leveraging dense 3D prior and explicit representations. Unfortunately, the benefits of the prior and representation do not involve novel view synthesis for dynamic motions. Ironically, this is because the main barrier is the reliance on them, which requires increasing training and rendering times to account for dynamic motions. In this paper, we design a \Edited{Explicit 4D Gaussian Splatting(Ex4DGS)}. Our key idea is to firstly separate static and dynamic Gaussians during training, and to explicitly sample positions and rotations of the dynamic Gaussians at sparse timestamps. The sampled positions and rotations are then interpolated to represent both spatially and temporally continuous motions of objects in dynamic scenes as well as reducing computational cost. Additionally, we introduce a progressive training scheme and a point-backtracking technique that improves Ex4DGS's convergence. We initially train Ex4DGS using short timestamps and progressively extend timestamps, which makes it work well with a few point clouds. The point-backtracking is used to quantify the cumulative error of each Gaussian over time, enabling the detection and removal of erroneous Gaussians in dynamic scenes. Comprehensive experiments on various scenes demonstrate the state-of-the-art rendering quality from our method, achieving fast rendering of 62 fps on a single 2080Ti GPU.📄 Paper | 🌐 Project Page | 💻 Code
13. [3DV '25] EgoGaussian: Dynamic Scene Understanding from Egocentric Video with 3D Gaussian Splatting
Authors: Daiwei Zhang, Gengyan Li, Jiajie Li, Mickaël Bressieux, Otmar Hilliges, Marc Pollefeys, Luc Van Gool, Xi Wang
Abstract Human activities are inherently complex, often involving numerous object interactions. To better understand these activities, it is crucial to model their interactions with the environment captured through dynamic changes. The recent availability of affordable head-mounted cameras and egocentric data offers a more accessible and efficient means to understand human-object interactions in 3D environments. However, most existing methods for human activity modeling neglect the dynamic interactions with objects, resulting in only static representations. The few existing solutions often require inputs from multiple sources, including multi-camera setups, depth-sensing cameras, or kinesthetic sensors. To this end, we introduce EgoGaussian, the first method capable of simultaneously reconstructing 3D scenes and dynamically tracking 3D object motion from RGB egocentric input alone. We leverage the uniquely discrete nature of Gaussian Splatting and segment dynamic interactions from the background, with both having explicit representations. Our approach employs a clip-level online learning pipeline that leverages the dynamic nature of human activities, allowing us to reconstruct the temporal evolution of the scene in chronological order and track rigid object motion. EgoGaussian shows significant improvements in terms of both dynamic object and background reconstruction quality compared to the state-of-the-art. We also qualitatively demonstrate the high quality of the reconstructed models.📄 Paper | 🌐 Project Page | 💻 Code | 🎥 Short Presentation
14. 3DGS-CD: 3D Gaussian Splatting-based Change Detection for Physical Object Rearrangement
Authors: Ziqi Lu, Jianbo Ye, John Leonard
Abstract We present 3DGS-CD, the first 3D Gaussian Splatting (3DGS)-based method for detecting physical object rearrangements in 3D scenes. Our approach estimates 3D object-level changes by comparing two sets of unaligned images taken at different times. Leveraging 3DGS's novel view rendering and EfficientSAM's zero-shot segmentation capabilities, we detect 2D object-level changes, which are then associated and fused across views to estimate 3D changes. Our method can detect changes in cluttered environments using sparse post-change images within as little as 18s, using as few as a single new image. It does not rely on depth input, user instructions, object classes, or object models -- An object is recognized simply if it has been re-arranged. Our approach is evaluated on both public and self-collected real-world datasets, achieving up to 14% higher accuracy and three orders of magnitude faster performance compared to the state-of-the-art radiance-field-based change detection method. This significant performance boost enables a broad range of downstream applications, where we highlight three key use cases: object reconstruction, robot workspace reset, and 3DGS model update. Our code and data will be made available at https://github.com/520xyxyzq/3DGS-CD.2023:
1. [3DV '24] Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis
Authors: Jonathon Luiten, Georgios Kopanas, Bastian Leibe, Deva Ramanan
Abstract We present a method that simultaneously addresses the tasks of dynamic scene novel-view synthesis and six degree-of-freedom (6-DOF) tracking of all dense scene elements. We follow an analysis-by-synthesis framework, inspired by recent work that models scenes as a collection of 3D Gaussians which are optimized to reconstruct input images via differentiable rendering. To model dynamic scenes, we allow Gaussians to move and rotate over time while enforcing that they have persistent color, opacity, and size. By regularizing Gaussians’ motion and rotation with local rigidity constraints, we show that our Dynamic 3D Gaussians correctly model the same area of physical space over time, including the rotation of that space. Dense 6-DOF tracking and dynamic reconstruction emerges naturally from persistent dynamic view synthesis, without requiring any correspondence or flow as input. We demonstrate a large number of downstream applications enabled by our representation, including first-person view synthesis, dynamic compositional scene synthesis, and 4D video editing.📄 Paper | 🌐 Project Page | 💻 Code | 🎥 Explanation Video
2. [CVPR '24] Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction
Authors: Ziyi Yang, Xinyu Gao, Wen Zhou, Shaohui Jiao, Yuqing Zhang, Xiaogang Jin
Abstract Implicit neural representation has opened up new avenues for dynamic scene reconstruction and rendering. Nonetheless, state-of-the-art methods of dynamic neural rendering rely heavily on these implicit representations, which frequently struggle with accurately capturing the intricate details of objects in the scene. Furthermore, implicit methods struggle to achieve real-time rendering in general dynamic scenes, limiting their use in a wide range of tasks. To address the issues, we propose a deformable 3D Gaussians Splatting method that reconstructs scenes using explicit 3D Gaussians and learns Gaussians in canonical space with a deformation field to model monocular dynamic scenes. We also introduced a smoothing training mechanism with no extra overhead to mitigate the impact of inaccurate poses in real datasets on the smoothness of time interpolation tasks. Through differential gaussian rasterization, the deformable 3D Gaussians not only achieve higher rendering quality but also real-time rendering speed. Experiments show that our method outperforms existing methods significantly in terms of both rendering quality and speed, making it well-suited for tasks such as novel-view synthesis, time synthesis, and real-time rendering.📄 Paper | 🌐 Project Page | 💻 Code
3. [CVPR '24] 4D Gaussian Splatting for Real-Time Dynamic Scene Rendering
Authors: Guanjun Wu, Taoran Yi, Jiemin Fang, Lingxi Xie, Xiaopeng Zhang, Wei Wei, Wenyu Liu, Tian Qi, Xinggang Wang
Abstract Representing and rendering dynamic scenes has been an important but challenging task. Especially, to accurately model complex motions, high efficiency is usually hard to maintain. We introduce the 4D Gaussian Splatting (4D-GS) to achieve real-time dynamic scene rendering while also enjoying high training and storage efficiency. An efficient deformation field is constructed to model both Gaussian motions and shape deformations. Different adjacent Gaussians are connected via a HexPlane to produce more accurate position and shape deformations. Our 4D-GS method achieves real-time rendering under high resolutions, 70 FPS at a 800×800 resolution on an RTX 3090 GPU, while maintaining comparable or higher quality than previous state-of-the-art method.📄 Paper | 🌐 Project Page | 💻 Code
4. Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting
Authors: Zeyu Yang, Hongye Yang, Zijie Pan, Xiatian Zhu, Li Zhang
Abstract Reconstructing dynamic 3D scenes from 2D images and generating diverse views over time is challenging due to scene complexity and temporal dynamics. Despite advancements in neural implicit models, limitations persist: (i) Inadequate Scene Structure: Existing methods struggle to reveal the spatial and temporal structure of dynamic scenes from directly learning the complex 6D plenoptic function. (ii) Scaling Deformation Modeling: Explicitly modeling scene element deformation becomes impractical for complex dynamics. To address these issues, we consider the spacetime as an entirety and propose to approximate the underlying spatio-temporal 4D volume of a dynamic scene by optimizing a collection of 4D primitives, with explicit geometry and appearance modeling. Learning to optimize the 4D primitives enables us to synthesize novel views at any desired time with our tailored rendering routine. Our model is conceptually simple, consisting of a 4D Gaussian parameterized by anisotropic ellipses that can rotate arbitrarily in space and time, as well as view-dependent and time-evolved appearance represented by the coefficient of 4D spherindrical harmonics. This approach offers simplicity, flexibility for variable-length video and end-to-end training, and efficient real-time rendering, making it suitable for capturing complex dynamic scene motions. Experiments across various benchmarks, including monocular and multi-view scenarios, demonstrate our 4DGS model's superior visual quality and efficiency.5. [ECCV '24] A Compact Dynamic 3D Gaussian Representation for Real-Time Dynamic View Synthesis
Authors: Kai Katsumata, Duc Minh Vo, Hideki Nakayama
Abstract In novel view synthesis of scenes from multiple input views, 3D Gaussian splatting emerges as a viable alternative to existing radiance field approaches, delivering great visual quality and real-time rendering. While successful in static scenes, the present advancement of 3D Gaussian representation, however, faces challenges in dynamic scenes in terms of memory consumption and the need for numerous observations per time step, due to the onus of storing 3D Gaussian parameters per time step. In this study, we present an efficient 3D Gaussian representation tailored for dynamic scenes in which we define positions and rotations as functions of time while leaving other time-invariant properties of the static 3D Gaussian unchanged. Notably, our representation reduces memory usage, which is consistent regardless of the input sequence length. Additionally, it mitigates the risk of overfitting observed frames by accounting for temporal changes. The optimization of our Gaussian representation based on image and flow reconstruction results in a powerful framework for dynamic scene view synthesis in both monocular and multi-view cases. We obtain the highest rendering speed of 118 frames per second (FPS) at a resolution of 1352×1014 with a single GPU, showing the practical usability and effectiveness of our proposed method in dynamic scene rendering scenarios📄 Paper | 🌐 Project Page | 💻 Code
6. DynMF: Neural Motion Factorization for Real-time Dynamic View Synthesis with 3D Gaussian Splatting
Authors: Agelos Kratimenos, Jiahui Lei, Kostas Daniilidis
Abstract Accurately and efficiently modeling dynamic scenes and motions is considered so challenging a task due to temporal dynamics and motion complexity. To address these challenges, we propose DynMF, a compact and efficient representation that decomposes a dynamic scene into a few neural trajectories. We argue that the per-point motions of a dynamic scene can be decomposed into a small set of explicit or learned trajectories. Our carefully designed neural framework consisting of a tiny set of learned basis queried only in time allows for rendering speed similar to 3D Gaussian Splatting, surpassing 120 FPS, while at the same time, requiring only double the storage compared to static scenes. Our neural representation adequately constrains the inherently underconstrained motion field of a dynamic scene leading to effective and fast optimization. This is done by biding each point to motion coefficients that enforce the per-point sharing of basis trajectories. By carefully applying a sparsity loss to the motion coefficients, we are able to disentangle the motions that comprise the scene, independently control them, and generate novel motion combinations that have never been seen before. We can reach state-of-the-art render quality within just 5 minutes of training and in less than half an hour, we can synthesize novel views of dynamic scenes with superior photorealistic quality. Our representation is interpretable, efficient, and expressive enough to offer real-time view synthesis of complex dynamic scene motions, in monocular and multi-view scenarios.📄 Paper | 🌐 Project Page | 💻 Code (not yet)
7. [CVPR '24] Control4D: Efficient 4D Portrait Editing with Text
Authors: Ruizhi Shao, Jingxiang Sun, Cheng Peng, Zerong Zheng, Boyao Zhou, Hongwen Zhang, Yebin Liu
Abstract We introduce Control4D, an innovative framework for editing dynamic 4D portraits using text instructions. Our method addresses the prevalent challenges in 4D editing, notably the inefficiencies of existing 4D representations and the inconsistent editing effect caused by diffusion-based editors. We first propose GaussianPlanes, a novel 4D representation that makes Gaussian Splatting more structured by applying plane-based decomposition in 3D space and time. This enhances both efficiency and robustness in 4D editing. Furthermore, we propose to leverage a 4D generator to learn a more continuous generation space from inconsistent edited images produced by the diffusion-based editor, which effectively improves the consistency and quality of 4D editing. Comprehensive evaluation demonstrates the superiority of Control4D, including significantly reduced training time, high-quality rendering, and spatial-temporal consistency in 4D portrait editing.📄 Paper | 🌐 Project Page | 💻 Code (not yet)
8. [CVPR '24] SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenes
Authors: Yi-Hua Huang, Yang-Tian Sun, Ziyi Yang, Xiaoyang Lyu, Yan-Pei Cao, Xiaojuan Qi
Abstract Novel view synthesis for dynamic scenes is still a challenging problem in computer vision and graphics. Recently, Gaussian splatting has emerged as a robust technique to represent static scenes and enable high-quality and real-time novel view synthesis. Building upon this technique, we propose a new representation that explicitly decomposes the motion and appearance of dynamic scenes into sparse control points and dense Gaussians, respectively. Our key idea is to use sparse control points, significantly fewer in number than the Gaussians, to learn compact 6 DoF transformation bases, which can be locally interpolated through learned interpolation weights to yield the motion field of 3D Gaussians. We employ a deformation MLP to predict time-varying 6 DoF transformations for each control point, which reduces learning complexities, enhances learning abilities, and facilitates obtaining temporal and spatial coherent motion patterns. Then, we jointly learn the 3D Gaussians, the canonical space locations of control points, and the deformation MLP to reconstruct the appearance, geometry, and dynamics of 3D scenes. During learning, the location and number of control points are adaptively adjusted to accommodate varying motion complexities in different regions, and an ARAP loss following the principle of as rigid as possible is developed to enforce spatial continuity and local rigidity of learned motions. Finally, thanks to the explicit sparse motion representation and its decomposition from appearance, our method can enable user-controlled motion editing while retaining high-fidelity appearances. Extensive experiments demonstrate that our approach outperforms existing approaches on novel view synthesis with a high rendering speed and enables novel appearance-preserved motion editing applications.📄 Paper | 🌐 Project Page | 💻 Code
9. [CVPR '24] Neural Parametric Gaussians for Monocular Non-Rigid Object Reconstruction
Authors: Devikalyan Das, Christopher Wewer, Raza Yunus, Eddy Ilg, Jan Eric Lenssen
Abstract Reconstructing dynamic objects from monocular videos is a severely underconstrained and challenging problem, and recent work has approached it in various directions. However, owing to the ill-posed nature of this problem, there has been no solution that can provide consistent, highquality novel views from camera positions that are significantly different from the training views. In this work, we introduce Neural Parametric Gaussians (NPGs) to take on this challenge by imposing a two-stage approach: first, we fit a low-rank neural deformation model, which then is used as regularization for non-rigid reconstruction in the second stage. The first stage learns the object’s deformations such that it preserves consistency in novel views. The second stage obtains high reconstruction quality by optimizing 3D Gaussians that are driven by the coarse model. To this end, we introduce a local 3D Gaussian representation, where temporally shared Gaussians are anchored in and deformed by local oriented volumes. The resulting combined model can be rendered as radiance fields, resulting in high-quality photo-realistic reconstructions of the non-rigidly deforming objects, maintaining 3D consistency across novel views. We demonstrate that NPGs achieve superior results compared to previous works, especially in challenging scenarios with few multi-view cues.10. [CVPR '24] Gaussian-Flow: 4D Reconstruction with Dynamic 3D Gaussian Particle
Authors: Youtian Lin, Zuozhuo Dai, Siyu Zhu, Yao Yao
Abstract We introduce Gaussian-Flow, a novel point-based approach for fast dynamic scene reconstruction and real-time rendering from both multi-view and monocular videos. In contrast to the prevalent NeRF-based approaches hampered by slow training and rendering speeds, our approach harnesses recent advancements in point-based 3D Gaussian Splatting (3DGS). Specifically, a novel Dual-Domain Deformation Model (DDDM) is proposed to explicitly model attribute deformations of each Gaussian point, where the time-dependent residual of each attribute is captured by a polynomial fitting in the time domain, and a Fourier series fitting in the frequency domain. The proposed DDDM is capable of modeling complex scene deformations across long video footage, eliminating the need for training separate 3DGS for each frame or introducing an additional implicit neural field to model 3D dynamics. Moreover, the explicit deformation modeling for discretized Gaussian points ensures ultra-fast training and rendering of a 4D scene, which is comparable to the original 3DGS designed for static 3D reconstruction. Our proposed approach showcases a substantial efficiency improvement, achieving a 5× faster training speed compared to the per-frame 3DGS modeling. In addition, quantitative results demonstrate that the proposed Gaussian-Flow significantly outperforms previous leading methods in novel view rendering quality.📄 Paper | 🌐 Project Page | 💻 Code (not yet)
11. [CVPR '24] CoGS: Controllable Gaussian Splatting
Authors: Heng Yu, Joel Julin, Zoltán Á. Milacski, Koichiro Niinuma, László A. Jeni
Abstract Capturing and re-animating the 3D structure of articulated objects present significant barriers. On one hand, methods requiring extensively calibrated multi-view setups are prohibitively complex and resource-intensive, limiting their practical applicability. On the other hand, while single-camera Neural Radiance Fields (NeRFs) offer a more streamlined approach, they have excessive training and rendering costs. 3D Gaussian Splatting would be a suitable alternative but for two reasons. Firstly, existing methods for 3D dynamic Gaussians require synchronized multi-view cameras, and secondly, the lack of controllability in dynamic scenarios. We present CoGS, a method for Controllable Gaussian Splatting, that enables the direct manipulation of scene elements, offering real-time control of dynamic scenes without the prerequisite of pre-computing control signals. We evaluated CoGS using both synthetic and real-world datasets that include dynamic objects that differ in degree of difficulty. In our evaluations, CoGS consistently outperformed existing dynamic and controllable neural representations in terms of visual fidelity.📄 Paper | 🌐 Project Page | 💻 Code (not yet)
12. GauFRe: Gaussian Deformation Fields for Real-time Dynamic Novel View Synthesis
Authors: Yiqing Liang, Numair Khan, Zhengqin Li, Thu Nguyen-Phuoc, Douglas Lanman, James Tompkin, Lei Xiao
Abstract We propose a method for dynamic scene reconstruction using deformable 3D Gaussians that is tailored for monocular video. Building upon the efficiency of Gaussian splatting, our approach extends the representation to accommodate dynamic elements via a deformable set of Gaussians residing in a canonical space, and a time-dependent deformation field defined by a multi-layer perceptron (MLP). Moreover, under the assumption that most natural scenes have large regions that remain static, we allow the MLP to focus its representational power by additionally including a static Gaussian point cloud. The concatenated dynamic and static point clouds form the input for the Gaussian Splatting rasterizer, enabling real-time rendering. The differentiable pipeline is optimized end-to-end with a self-supervised rendering loss. Our method achieves results that are comparable to state-of-the-art dynamic neural radiance field methods while allowing much faster optimization and rendering.📄 Paper | 🌐 Project Page | 🎥 Short Presentation
13. [CVPR '24] Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesis
Authors: Zhan Li, Zhang Chen, Zhong Li, Yi Xu
Abstract Novel view synthesis of dynamic scenes has been an intriguing yet challenging problem. Despite recent advancements, simultaneously achieving high-resolution photorealistic results, real-time rendering, and compact storage remains a formidable task. To address these challenges, we propose Spacetime Gaussian Feature Splatting as a novel dynamic scene representation, composed of three pivotal components. First, we formulate expressive Spacetime Gaussians by enhancing 3D Gaussians with temporal opacity and parametric motion/rotation. This enables Spacetime Gaussians to capture static, dynamic, as well as transient content within a scene. Second, we introduce splatted feature rendering, which replaces spherical harmonics with neural features. These features facilitate the modeling of view- and time-dependent appearance while maintaining small size. Third, we leverage the guidance of training error and coarse depth to sample new Gaussians in areas that are challenging to converge with existing pipelines. Experiments on several established real-world datasets demonstrate that our method achieves state-of-the-art rendering quality and speed, while retaining compact storage. At 8K resolution, our lite-version model can render at 60 FPS on an Nvidia RTX 4090 GPU.📄 Paper | 🌐 Project Page | 💻 Code | 🎥 Short Presentation
14. MD-Splatting: Learning Metric Deformation from 4D Gaussians in Highly Deformable Scenes
Authors: Bardienus P. Duisterhof, Zhao Mandi, Yunchao Yao, Jia-Wei Liu, Mike Zheng Shou, Shuran Song, Jeffrey Ichnowski
Abstract Accurate 3D tracking in highly deformable scenes with occlusions and shadows can facilitate new applications in robotics, augmented reality, and generative AI. However, tracking under these conditions is extremely challenging due to the ambiguity that arises with large deformations, shadows, and occlusions. We introduce MD-Splatting, an approach for simultaneous 3D tracking and novel view synthesis, using video captures of a dynamic scene from various camera poses. MD-Splatting builds on recent advances in Gaussian splatting, a method that learns the properties of a large number of Gaussians for state-of-the-art and fast novel view synthesis. MD-Splatting learns a deformation function to project a set of Gaussians with non-metric, thus canonical, properties into metric space. The deformation function uses a neural-voxel encoding and a multilayer perceptron (MLP) to infer Gaussian position, rotation, and a shadow scalar. We enforce physics-inspired regularization terms based on local rigidity, conservation of momentum, and isometry, which leads to trajectories with smaller trajectory errors. MD-Splatting achieves high-quality 3D tracking on highly deformable scenes with shadows and occlusions. Compared to state-of-the-art, we improve 3D tracking by an average of 23.9 %, while simultaneously achieving high-quality novel view synthesis. With sufficient texture such as in scene 6, MD-Splatting achieves a median tracking error of 3.39 mm on a cloth of 1 x 1 meters in size📄 Paper | 🌐 Project Page | 💻 Code (not yet)
15. [ECCV '24] SWinGS: Sliding Windows for Dynamic 3D Gaussian Splatting
Authors: Richard Shaw, Michal Nazarczuk, Jifei Song, Arthur Moreau, Sibi Catley-Chandar, Helisa Dhamo, Eduardo Perez-Pellitero
Abstract Novel view synthesis has shown rapid progress recently, with methods capable of producing increasingly photorealistic results. 3D Gaussian Splatting has emerged as a promising method, producing high-quality renderings of scenes and enabling interactive viewing at real-time frame rates. However, it is limited to static scenes. In this work, we extend 3D Gaussian Splatting to reconstruct dynamic scenes. We model a scene's dynamics using dynamic MLPs, learning deformations from temporally-local canonical representations to per-frame 3D Gaussians. To disentangle static and dynamic regions, tuneable parameters weigh each Gaussian's respective MLP parameters, improving the dynamics modelling of imbalanced scenes. We introduce a sliding window training strategy that partitions the sequence into smaller manageable windows to handle arbitrary length scenes while maintaining high rendering quality. We propose an adaptive sampling strategy to determine appropriate window size hyperparameters based on the scene's motion, balancing training overhead with visual quality. Training a separate dynamic 3D Gaussian model for each sliding window allows the canonical representation to change, enabling the reconstruction of scenes with significant geometric changes. Temporal consistency is enforced using a fine-tuning step with self-supervising consistency loss on randomly sampled novel views. As a result, our method produces high-quality renderings of general dynamic scenes with competitive quantitative performance, which can be viewed in real-time in our dynamic interactive viewer.16. [CVPR '24] 3DGStream: On-the-Fly Training of 3D Gaussians for Efficient Streaming of Photo-Realistic Free-Viewpoint Videos
Authors: Jiakai Sun, Han Jiao, Guangyuan Li, Zhanjie Zhang, Lei Zhao, Wei Xing
Abstract Constructing photo-realistic Free-Viewpoint Videos (FVVs) of dynamic scenes from multi-view videos remains a challenging endeavor. Despite the remarkable advancements achieved by current neural rendering techniques, these methods generally require complete video sequences for offline training and are not capable of real-time rendering. To address these constraints, we introduce 3DGStream, a method designed for efficient FVV streaming of real-world dynamic scenes. Our method achieves fast on-the-fly per-frame reconstruction within 12 seconds and real-time rendering at 200 FPS. Specificallggy, we utilize 3D Gaussians (3DGs) to represent the scene. Instead of the naïve approach of directly optimizing 3DGs per-frame, we employ a compact Neural Transformation Cache (NTC) to model the translations and rotations of 3DGs, markedly reducing the training time and storage required for each FVV frame. Furthermore, we propose an adaptive 3DG addition strategy to handle emerging objects in dynamic scenes. Experiments demonstrate that 3DGStream achieves competitive performance in terms of rendering speed, image quality, training time, and model storage when compared with state-of-the-art methods.📄 Paper | 🌐 Project Page | 💻 Code (not yet) | 🔍 3DGStream Viewer
Editing:
2024:
1. Contrastive Gaussian Clustering: Weakly Supervised 3D Scene Segmentation
Authors: Myrna C. Silva, Mahtab Dahaghin, Matteo Toso, Alessio Del Bue
Abstract We introduce Contrastive Gaussian Clustering, a novel approach capable of provide segmentation masks from any viewpoint and of enabling 3D segmentation of the scene. Recent works in novel-view synthesis have shown how to model the appearance of a scene via a cloud of 3D Gaussians, and how to generate accurate images from a given viewpoint by projecting on it the Gaussians before α blending their color. Following this example, we train a model to include also a segmentation feature vector for each Gaussian. These can then be used for 3D scene segmentation, by clustering Gaussians according to their feature vectors; and to generate 2D segmentation masks, by projecting the Gaussians on a plane and α blending over their segmentation features. Using a combination of contrastive learning and spatial regularization, our method can be trained on inconsistent 2D segmentation masks, and still learn to generate segmentation masks consistent across all views. Moreover, the resulting model is extremely accurate, improving the IoU accuracy of the predicted masks by +8% over the state of the art. Code and trained models will be released upon acceptance.2. CoSSegGaussians: Compact and Swift Scene Segmenting 3D Gaussians
Authors: Bin Dou, Tianyu Zhang, Yongjia Ma, Zhaohui Wang, Zejian Yuan
Abstract We propose Compact and Swift Segmenting 3D Gaussians(CoSSegGaussians), a method for compact 3D-consistent scene segmentation at fast rendering speed with only RGB images input. Previous NeRF-based 3D segmentation methods have relied on implicit or voxel neural scene representation and ray-marching volume rendering which are time consuming. Recent 3D Gaussian Splatting significantly improves the rendering speed, however, existing Gaussians-based segmentation methods(eg: Gaussian Grouping) fail to provide compact segmentation masks especially in zero-shot segmentation, which is mainly caused by the lack of robustness and compactness for straightforwardly assigning learnable parameters to each Gaussian when encountering inconsistent 2D machine-generated labels. Our method aims to achieve compact and reliable zero-shot scene segmentation swiftly by mapping fused spatial and semantically meaningful features for each Gaussian point with a shallow decoding network. Specifically, our method firstly optimizes Gaussian points’ position, convariance and color attributes under the supervision of RGB images. After Gaussian Locating, we distill multi-scale DINO features extracted from images through unprojection to each Gaussian, which is then incorporated with spatial features from the fast point features processing network, i.e. RandLA-Net. Then the shallow decoding MLP is applied to the multi-scale fused features to obtain compact segmentation. Experimental results show that our model can perform high-quality zero-shot scene segmentation, as our model outperforms other segmentation methods on both semantic and panoptic segmentation task, meanwhile consumes approximately only 10% segmenting time compared to NeRF-based segmentation.📄 Paper | 🌐 Project Page | 💻 Code (not yet)
3. TIP-Editor: An Accurate 3D Editor Following Both Text-Prompts And Image-Prompts
Authors: Jingyu Zhuang, Di Kang, Yan-Pei Cao, Guanbin Li, Liang Lin, Ying Shan
Abstract Text-driven 3D scene editing has gained significant attention owing to its convenience and user-friendliness. However, existing methods still lack accurate control of the specified appearance and location of the editing result due to the inherent limitations of the text description. To this end, we propose a 3D scene editing framework, TIPEditor, that accepts both text and image prompts and a 3D bounding box to specify the editing region. With the image prompt, users can conveniently specify the detailed appearance/style of the target content in complement to the text description, enabling accurate control of the appearance. Specifically, TIP-Editor employs a stepwise 2D personalization strategy to better learn the representation of the existing scene and the reference image, in which a localization loss is proposed to encourage correct object placement as specified by the bounding box. Additionally, TIPEditor utilizes explicit and flexible 3D Gaussian splatting as the 3D representation to facilitate local editing while keeping the background unchanged. Extensive experiments have demonstrated that TIP-Editor conducts accurate editing following the text and image prompts in the specified bounding box region, consistently outperforming the baselines in editing quality, and the alignment to the prompts, qualitatively and quantitatively.4. Segment Anything in 3D Gaussians
Authors: Xu Hu, Yuxi Wang, Lue Fan, Junsong Fan, Junran Peng, Zhen Lei, Qing Li, Zhaoxiang Zhang
Abstract 3D Gaussian Splatting has emerged as an alternative 3D representation of Neural Radiance Fields (NeRFs), benefiting from its high-quality rendering results and real-time rendering speed. Considering the 3D Gaussian representation remains unparsed, it is necessary first to execute object segmentation within this domain. Subsequently, scene editing and collision detection can be performed, proving vital to a multitude of applications, such as virtual reality (VR), augmented reality (AR), game/movie production, etc. In this paper, we propose a novel approach to achieve object segmentation in 3D Gaussian via an interactive procedure without any training process and learned parameters. We refer to the proposed method as SA-GS, for Segment Anything in 3D Gaussians. Given a set of clicked points in a single input view, SA-GS can generalize SAM to achieve 3D consistent segmentation via the proposed multi-view mask generation and view-wise label assignment methods. We also propose a cross-view label-voting approach to assign labels from different views. In addition, in order to address the boundary roughness issue of segmented objects resulting from the non-negligible spatial sizes of 3D Gaussian located at the boundary, SA-GS incorporates the simple but effective Gaussian Decomposition scheme. Extensive experiments demonstrate that SA-GS achieves high-quality 3D segmentation results, which can also be easily applied for scene editing and collision detection tasks.5. GSEdit: Efficient Text-Guided Editing of 3D Objects via Gaussian Splatting
Authors: Francesco Palandra, Andrea Sanchietti, Daniele Baieri, Emanuele Rodolà
Abstract We present GSEdit, a pipeline for text-guided 3D object editing based on Gaussian Splatting models. Our method enables the editing of the style and appearance of 3D objects without altering their main details, all in a matter of minutes on consumer hardware. We tackle the problem by leveraging Gaussian splatting to represent 3D scenes, and we optimize the model while progressively varying the image supervision by means of a pretrained image-based diffusion model. The input object may be given as a 3D triangular mesh, or directly provided as Gaussians from a generative model such as DreamGaussian. GSEdit ensures consistency across different viewpoints, maintaining the integrity of the original object's information. Compared to previously proposed methods relying on NeRF-like MLP models, GSEdit stands out for its efficiency, making 3D editing tasks much faster. Our editing process is refined via the application of the SDS loss, ensuring that our edits are both precise and accurate. Our comprehensive evaluation demonstrates that GSEdit effectively alters object shape and appearance following the given textual instructions while preserving their coherence and detail.6. GaussCtrl: Multi-View Consistent Text-Driven 3D Gaussian Splatting Editing
Authors: Jing Wu, Jia-Wang Bian, Xinghui Li, Guangrun Wang, Ian Reid, Philip Torr, Victor Adrian Prisacariu
Abstract We propose GaussCtrl, a text-driven method to edit a 3D scene reconstructed by the 3D Gaussian Splatting (3DGS). Our method first renders a collection of images by using the 3DGS and edits them by using a pre-trained 2D diffusion model (ControlNet) based on the input prompt, which is then used to optimise the 3D model. Our key contribution is multi-view consistent editing, which enables editing all images together instead of iteratively editing one image while updating the 3D model as in previous works. It leads to faster editing as well as higher visual quality. This is achieved by the two terms: (a) depth-conditioned editing that enforces geometric consistency across multi-view images by leveraging naturally consistent depth maps. (b) attention-based latent code alignment that unifies the appearance of edited images by conditioning their editing to several reference views through self and cross-view attention between images' latent representations. Experiments demonstrate that our method achieves faster editing and better visual results than previous state-of-the-art methods.7. View-Consistent 3D Editing with Gaussian Splatting
Authors: Yuxuan Wang, Xuanyu Yi, Zike Wu, Na Zhao, Long Chen, Hanwang Zhang
Abstract The advent of 3D Gaussian Splatting (3DGS) has revolutionized 3D editing, offering efficient, high-fidelity rendering and enabling precise local manipulations. Currently, diffusion-based 2D editing models are harnessed to modify multi-view rendered images, which then guide the editing of 3DGS models. However, this approach faces a critical issue of multi-view inconsistency, where the guidance images exhibit significant discrepancies across views, leading to mode collapse and visual artifacts of 3DGS. To this end, we introduce View-consistent Editing (VcEdit), a novel framework that seamlessly incorporates 3DGS into image editing processes, ensuring multi-view consistency in edited guidance images and effectively mitigating mode collapse issues. VcEdit employs two innovative consistency modules: the Cross-attention Consistency Module and the Editing Consistency Module, both designed to reduce inconsistencies in edited images. By incorporating these consistency modules into an iterative pattern, VcEdit proficiently resolves the issue of multi-view inconsistency, facilitating high-quality 3DGS editing across a diverse range of scenes.8. Gaussian Frosting: Editable Complex Radiance Fields with Real-Time Rendering
Authors: Antoine Guédon, Vincent Lepetit
Abstract We propose Gaussian Frosting, a novel mesh-based representation for high-quality rendering and editing of complex 3D effects in real-time. Our approach builds on the recent 3D Gaussian Splatting framework, which optimizes a set of 3D Gaussians to approximate a radiance field from images. We propose first extracting a base mesh from Gaussians during optimization, then building and refining an adaptive layer of Gaussians with a variable thickness around the mesh to better capture the fine details and volumetric effects near the surface, such as hair or grass. We call this layer Gaussian Frosting, as it resembles a coating of frosting on a cake. The fuzzier the material, the thicker the frosting. We also introduce a parameterization of the Gaussians to enforce them to stay inside the frosting layer and automatically adjust their parameters when deforming, rescaling, editing or animating the mesh. Our representation allows for efficient rendering using Gaussian splatting, as well as editing and animation by modifying the base mesh. We demonstrate the effectiveness of our method on various synthetic and real scenes, and show that it outperforms existing surface-based approaches. We will release our code and a web-based viewer as additional contributions.📄 Paper | 🌐 Project Page | 💻 Code (not yet) | 🎥 Short Presentation
9. Semantic Gaussians: Open-Vocabulary Scene Understanding with 3D Gaussian Splatting
Authors: Jun Guo, Xiaojian Ma, Yue Fan, Huaping Liu, Qing Li
Abstract Open-vocabulary 3D scene understanding presents a significant challenge in computer vision, withwide-ranging applications in embodied agents and augmented reality systems. Previous approaches haveadopted Neural Radiance Fields (NeRFs) to analyze 3D scenes. In this paper, we introduce SemanticGaussians, a novel open-vocabulary scene understanding approach based on 3D Gaussian Splatting. Our keyidea is distilling pre-trained 2D semantics into 3D Gaussians. We design a versatile projection approachthat maps various 2Dsemantic features from pre-trained image encoders into a novel semantic component of 3D Gaussians, withoutthe additional training required by NeRFs. We further build a 3D semantic network that directly predictsthe semantic component from raw 3D Gaussians for fast inference. We explore several applications ofSemantic Gaussians: semantic segmentation on ScanNet-20, where our approach attains a 4.2% mIoU and 4.0%mAcc improvement over prior open-vocabulary scene understanding counterparts; object part segmentation,sceneediting, and spatial-temporal segmentation with better qualitative results over 2D and 3D baselines,highlighting its versatility and effectiveness on supporting diverse downstream tasks.📄 Paper | 🌐 Project Page | 💻 Code (not yet)
10. EgoLifter: Open-world 3D Segmentation for Egocentric Perception
Authors: Qiao Gu, Zhaoyang Lv, Duncan Frost, Simon Green, Julian Straub, Chris Sweeney
Abstract In this paper we present EgoLifter, a novel system that can automatically segment scenes captured from egocentric sensors into a complete decomposition of individual 3D objects. The system is specifically designed for egocentric data where scenes contain hundreds of objects captured from natural (non-scanning) motion. EgoLifter adopts 3D Gaussians as the underlying representation of 3D scenes and objects and uses segmentation masks from the Segment Anything Model (SAM) as weak supervision to learn flexible and promptable definitions of object instances free of any specific object taxonomy. To handle the challenge of dynamic objects in ego-centric videos, we design a transient prediction module that learns to filter out dynamic objects in the 3D reconstruction. The result is a fully automatic pipeline that is able to reconstruct 3D object instances as collections of 3D Gaussians that collectively compose the entire scene. We created a new benchmark on the Aria Digital Twin dataset that quantitatively demonstrates its state-of-the-art performance in open-world 3D segmentation from natural egocentric input. We run EgoLifter on various egocentric activity datasets which shows the promise of the method for 3D egocentric perception at scale.📄 Paper | 🌐 Project Page | 💻 Code (not yet)
11. InFusion: Inpainting 3D Gaussians via Learning Depth Completion from Diffusion Prior
Authors: Zhiheng Liu, Hao Ouyang, Qiuyu Wang, Ka Leong Cheng, Jie Xiao, Kai Zhu, Nan Xue, Yu Liu, Yujun Shen, Yang Cao
Abstract 3D Gaussians have recently emerged as an efficient representation for novel view synthesis. This work studies its editability with a particular focus on the inpainting task, which aims to supplement an incomplete set of 3D Gaussians with additional points for visually harmonious rendering. Compared to 2D inpainting, the crux of inpainting 3D Gaussians is to figure out the rendering-relevant properties of the introduced points, whose optimization largely benefits from their initial 3D positions. To this end, we propose to guide the point initialization with an image-conditioned depth completion model, which learns to directly restore the depth map based on the observed image. Such a design allows our model to fill in depth values at an aligned scale with the original depth, and also to harness strong generalizability from largescale diffusion prior. Thanks to the more accurate depth completion, our approach, dubbed InFusion, surpasses existing alternatives with sufficiently better fidelity and efficiency under various complex scenarios. We further demonstrate the effectiveness of InFusion with several practical applications, such as inpainting with user-specific texture or with novel object insertion.📄 Paper | [🌐 Project Page](https://j
扫一扫
2万+
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
