CVPR2024——3D

一、 3DGS(Gaussian Splatting)

1. Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering

• Homepage: Scaffold-GS: Structured 3D Gaussians for View-Adaptive RenderingScaffold-GS: Structured 3D Gaussians for View-Adaptive Renderinghttps://city-super.github.io/scaffold-gs/
• Paper: https://arxiv.org/abs/2312.00109https://arxiv.org/abs/2312.00109
• Code: GitHub - city-super/Scaffold-GS: [CVPR 2024 Highlight] Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering[CVPR 2024 Highlight] Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering - city-super/Scaffold-GShttps://github.com/city-super/Scaffold-GS

2. GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesis

• Homepage: Projectpage of GPS-Gaussianhttps://shunyuanzheng.github.io/GPS-Gaussian
• Paper: https://arxiv.org/abs/2312.02155https://arxiv.org/abs/2312.02155
• Code: GitHub - aipixel/GPS-Gaussian: [CVPR 2024 Highlight] The official repo for “GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesis”[CVPR 2024 Highlight] The official repo for “GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesis” - aipixel/GPS-Gaussianhttps://github.com/ShunyuanZheng/GPS-Gaussian

3. GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D Gaussians

• Paper: https://arxiv.org/abs/2312.02134https://arxiv.org/abs/2312.02134
• Code: GitHub - aipixel/GaussianAvatar: [CVPR 2024] The official repo for "GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D Gaussians"[CVPR 2024] The official repo for "GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D Gaussians" - aipixel/GaussianAvatarhttps://github.com/huliangxiao/GaussianAvatar

4. GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting

• Paper: https://arxiv.org/abs/2311.14521https://arxiv.org/abs/2311.14521
• Code: GitHub - buaacyw/GaussianEditor: [CVPR 2024] GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting[CVPR 2024] GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting - buaacyw/GaussianEditorhttps://github.com/buaacyw/GaussianEditor

5. Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction

• Homepage: Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene ReconstructionDeformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstructionhttps://ingra14m.github.io/Deformable-Gaussians/
• Paper: https://arxiv.org/abs/2309.13101https://arxiv.org/abs/2309.13101
• Code: GitHub - ingra14m/Deformable-3D-Gaussians: [CVPR 2024] Official implementation of "Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction"[CVPR 2024] Official implementation of "Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction" - ingra14m/Deformable-3D-Gaussianshttps://github.com/ingra14m/Deformable-3D-Gaussians

6. SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenes

• Homepage: SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic ScenesSC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Sceneshttps://yihua7.github.io/SC-GS-web/
• Paper: https://arxiv.org/abs/2312.14937https://arxiv.org/abs/2312.14937
• Code: GitHub - yihua7/SC-GS: [CVPR 2024] Code for SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenes[CVPR 2024] Code for SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenes - yihua7/SC-GShttps://github.com/yihua7/SC-GS

7. Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesis

• Homepage: Spacetime Gaussian Feature Splatting for Real-Time Dynamic View SynthesisSpacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesishttps://oppo-us-research.github.io/SpacetimeGaussians-website/
• Paper: https://arxiv.org/abs/2312.16812https://arxiv.org/abs/2312.16812
• Code: GitHub - oppo-us-research/SpacetimeGaussians: [CVPR 2024] Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesis[CVPR 2024] Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesis - oppo-us-research/SpacetimeGaussianshttps://github.com/oppo-us-research/SpacetimeGaussians

8. DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalization

• Homepage: DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth NormalizationEfficient Region-Aware Neural Radiance Fields for High-Fidelity Talking Portrait Synthesis.https://fictionarry.github.io/DNGaussian/
• Paper: https://arxiv.org/abs/2403.06912https://arxiv.org/abs/2403.06912
• Code: GitHub - Fictionarry/DNGaussian: [CVPR'24] DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalization[CVPR'24] DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalization - Fictionarry/DNGaussianhttps://github.com/Fictionarry/DNGaussian

9. 4D Gaussian Splatting for Real-Time Dynamic Scene Rendering

• Paper: https://arxiv.org/abs/2310.08528https://arxiv.org/abs/2310.08528
• Code: GitHub - hustvl/4DGaussians: [CVPR 2024] 4D Gaussian Splatting for Real-Time Dynamic Scene Rendering[CVPR 2024] 4D Gaussian Splatting for Real-Time Dynamic Scene Rendering - hustvl/4DGaussianshttps://github.com/hustvl/4DGaussians

10. GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion Models

• Paper: https://arxiv.org/abs/2310.08529https://arxiv.org/abs/2310.08529
• Code: GitHub - hustvl/GaussianDreamer: GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion Models (CVPR 2024)GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion Models (CVPR 2024) - hustvl/GaussianDreamerhttps://github.com/hustvl/GaussianDreamer

二、 3D目标检测(3D Object Detection)

1. PTT: Point-Trajectory Transformer for Efficient Temporal 3D Object Detection

• Paper: https://arxiv.org/abs/2312.08371https://arxiv.org/abs/2312.08371
• Code: GitHub - KuanchihHuang/PTT: [CVPR2024] PTT: Point-Trajectory Transformer for Efficient Temporal 3D Object Detection[CVPR2024] PTT: Point-Trajectory Transformer for Efficient Temporal 3D Object Detection - KuanchihHuang/PTThttps://github.com/kuanchihhuang/PTT

2. UniMODE: Unified Monocular 3D Object Detection

• Paper: https://arxiv.org/abs/2402.18573https://arxiv.org/abs/2402.18573

三、 3D人体姿态估计(3D Human Pose Estimation)

1. Hourglass Tokenizer for Efficient Transformer-Based 3D Human Pose Estimation

• Paper: https://arxiv.org/abs/2311.12028https://arxiv.org/abs/2311.12028
• Code: GitHub - NationalGAILab/HoT: [CVPR 2024 🔥] Official implementation of the paper "⏳ Hourglass Tokenizer for Efficient Transformer-Based 3D Human Pose Estimation"[CVPR 2024 🔥] Official implementation of the paper "⏳ Hourglass Tokenizer for Efficient Transformer-Based 3D Human Pose Estimation" - NationalGAILab/HoThttps://github.com/NationalGAILab/HoT

四、3D生成

1. CityDreamer: Compositional Generative Model of Unbounded 3D Cities

• Homepage: City Dreamer | Infinite Scripthttps://haozhexie.com/project/city-dreamer/
• Paper: https://arxiv.org/abs/2309.00610https://arxiv.org/abs/2309.00610
• Code: GitHub - hzxie/CityDreamer: The official implementation of "CityDreamer: Compositional Generative Model of Unbounded 3D Cities". (Xie et al., CVPR 2024)The official implementation of "CityDreamer: Compositional Generative Model of Unbounded 3D Cities". (Xie et al., CVPR 2024) - hzxie/CityDreamerhttps://github.com/hzxie/city-dreamer

2. LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matching

• Paper: https://arxiv.org/abs/2311.11284https://arxiv.org/abs/2311.11284
• Code: GitHub - EnVision-Research/LucidDreamer: Official implementation of "LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matching"Official implementation of "LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matching" - EnVision-Research/LucidDreamerhttps://github.com/EnVision-Research/LucidDreamer