人体三维重建【文章汇总】Humans
- 【ECCV 2020 (oral)】NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis
- 【ACM_2023】3D Gaussian Splatting for Real-Time Radiance Field Rendering
- 【arxiv 2024.02】ImplicitDeepfake: Plausible Face-Swapping through Implicit Deepfake Generation using NeRF and Gaussian Splatting
- 【CVPR 2024】GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians
- 【arxiv 2024.01】En3D: An Enhanced Generative Model for Sculpting 3D Humans from 2D Synthetic Data
- 【ICCV 2023】ReFit: Recurrent Fitting Network for 3D Human Recovery
- 【ICCV 2023】Humans in 4D: Reconstructing and Tracking Humans with Transformers
- 【CVPR 2018】End-to-end Recovery of Human Shape and Pose
- 【CVPR2020】VIBE: Video Inference for Human Body Pose and Shape Estimation
- 【ICCV 2019】Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop
- 【2015】SMPL: A Skinned Multi-Person Linear Model
- 【ICCV 2021】ROMP:Monocular, One-stage, Regression of Multiple 3D People
- 【CVPR 2024】HumanRef: Single Image to 3D Human Generation via Reference-Guided Diffusion
- 【arxiv 2024.02】HumanSplat: Generalizable Single-Image Human Gaussian Splatting with Structure Priors
- 【CVPR 2024】GART: Gaussian Articulated Template Models
- 【CVPR 2023】ECON: Explicit Clothed humans Optimized via Normal integration
- 【CVPR 2024】MeshPose: Unifying DensePose and 3D Body Mesh reconstruction
- 【arxiv 2024.06】MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers
- 【arxiv 2024.06】Human 3Diffusion: Realistic Avatar Creation via Explicit 3D Consistent Diffusion Models
- 【arxiv 2024.06】A Survey on 3D Human Avatar Modeling -- From Reconstruction to Generation
- 【3DV 2024】TeCH: Text-guided Reconstruction of Lifelike Clothed Humans
- 【arxiv 2024.02】Sv3d: Novel multi-view synthesis and 3d generation from a single image using latent video diffusion.
- 【arxiv 2024.02】xxx
- 【arxiv 2024.02】xxx
- 【arxiv 2024.02】xxx
- 【arxiv 2024.02】xxx
- 【arxiv 2024.02】xxx
- 【arxiv 2024.02】xxx
- 【arxiv 2024.02】xxx
数据集
LSP, LSP-extended【lustered pose and nonlinear appearance models for human pose estimation】
MPII【2d human pose estimation: New benchmark and state of the art analysis】
MS COCO【Microsoft coco: Commonobjects in context.】
Human3.6M 【Human3.6M: Large scale datasets and predictive methods for 3D human sensing in natural environments. 】
MPI-INF-3DHP 【Vnect: Real-time 3d human pose estimation with a single rgb camera】
指标
MPJPE(Mean Per-Joint Position Error)
MPJPE直接衡量了预测关节坐标与真实关节坐标之间的欧几里得距离的平均值。具体来说,对于每一个关节j&#x