Research map / 3D vision / Face and shape
Dynamic FAUST: Registering Human Bodies in Motion
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 |
|---|---|---|---|
| add texture-based matching and appearance-based refinement to geometry-only registration | Dyna registrations · D-FAUST sequences | registration accuracy: 82% of scan points satisfy all three criteria | Helped |
| combine long-range reference-frame matches with short-range consecutive-frame matches (ablation) | Stage 1 match-based rectification · D-FAUST sequences | registration accuracy | Helped |
| remove short-range matches (ablation) | Stage 1 match-based rectification · D-FAUST sequences | registration accuracy | Hurt |
| remove long-range reference-frame matches (ablation) | Stage 1 match-based rectification · D-FAUST sequences | registration accuracy | Hurt |
| remove appearance-based registration after match-based rectification (ablation) | D-FAUST registrations · D-FAUST sequences | registration accuracy | Hurt |
| use geometry-only registration instead of geometry and texture (ablation) | Dyna registrations · D-FAUST sequences | alignment accuracy | Hurt |
Closest papers by meaning
- Fast 4D Mesh Generation by Spatio-Temporal Attention Chains (NeurIPS 2026 · similarity 0.86)
- Dynamic Neural Surfaces for Elastic 4D Shape Representation and Analysis (CVPR 2025 · similarity 0.85)
- 4D3R: Motion-Aware Neural Reconstruction and Rendering of Dynamic Scenes from Monocular Videos (NeurIPS 2025 · similarity 0.84)
- Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting (ICLR 2024 · similarity 0.84)
- MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion (ICLR 2025 · similarity 0.84)
- Diffusion4D: Fast Spatial-temporal Consistent 4D generation via Video Diffusion Models (NeurIPS 2024 · similarity 0.84)
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.