Research map / 3D vision / 3D generation
Learning Motion-Dependent Appearance for High-Fidelity Rendering of Dynamic Humans From a Single Camera
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use the proposed 3D motion descriptor and compositional renderer rather than DIW | Dynamic human rendering · YouTube 1, YouTube 2, YouTube 3, MPI, Custom 1, Custom 2 | SSIM and LPIPS ×100 | Helped |
| Add shape prediction (ablation) | Full rendering method · Custom 2 (15K) | LPIPS ×100: 4.31 -> 3.81 | Helped |
| Add shape prediction (ablation) | Full rendering method · Custom 2 (15K) | SSIM: 0.945 -> 0.946 | Helped |
| Add shape prediction (ablation) | Full rendering method · Custom 2 (15K) | tLPIPS ×100: 0.401 -> 0.404 | Hurt |
| Replace 3D motion descriptors with dense UV renderings as decoder input (ablation) | Full rendering method · Custom 2 | Perceptual quality | Hurt |
| Remove surface-normal prediction (ablation) | Full rendering method · Custom 2 | Perceptual quality | Hurt |
| Train with 10% of the original frames | Ours versus DIW · Custom 1 and Custom 2 | Generalization to unseen poses | Helped |
Closest papers by meaning
- SurMo: Surface-based 4D Motion Modeling for Dynamic Human Rendering (CVPR 2024 · similarity 0.91)
- IntrinsicAvatar: Physically Based Inverse Rendering of Dynamic Humans from Monocular Videos via Explicit Ray Tracing (CVPR 2024 · similarity 0.87)
- Link to the Past: Temporal Propagation for Fast 3D Human Reconstruction from Monocular Video (CVPR 2025 · similarity 0.87)
- 4D3R: Motion-Aware Neural Reconstruction and Rendering of Dynamic Scenes from Monocular Videos (NeurIPS 2025 · similarity 0.86)
- Holoported Characters: Real-time Free-viewpoint Rendering of Humans from Sparse RGB Cameras (CVPR 2024 · similarity 0.86)
- ODHSR: Online Dense 3D Reconstruction of Humans and Scenes from Monocular Videos (CVPR 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.