Research map / 3D vision / Face and shape
SNARF: Differentiable Forward Skinning for Animating Non-Rigid Neural Implicit Shapes
Xu Chen, Yufeng Zheng, Michael J. Black, Otmar Hilliges, Andreas Geiger
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 SNARF forward skinning instead of NASA | SNARF · DFaust within distribution | IoU bbox: 96.14% -> 97.31% | Improved |
| use SNARF forward skinning instead of NASA | SNARF · DFaust within distribution | IoU surface: 86.98% -> 90.38% | Improved |
| use SNARF forward skinning instead of NASA | SNARF · PosePrior out of distribution | IoU surface: 60.21% -> 80.65% | Improved |
| use SNARF forward skinning instead of NASA | SNARF · PosePrior out of distribution | IoU bbox: 83.16% -> 93.97% | Improved |
| use forward skinning instead of backward skinning (Back-LBS) | SNARF · PosePrior out of distribution | IoU surface: 68.93% -> 80.65% | Improved |
| use forward skinning instead of backward skinning (Back-LBS) | SNARF · DFaust within distribution | IoU bbox: 81.68% -> 97.31% | Improved |
| use skinning-based deformation instead of pose-conditioned occupancy network | SNARF · PosePrior out of distribution | IoU surface: 28.69% -> 80.65% | Improved |
| use skinning instead of backward displacement (Back-D) | SNARF · PosePrior out of distribution | IoU surface: 35.44% -> 80.65% | Improved |
Closest papers by meaning
- Implicit-ARAP: Efficient Handle-Guided Neural Field Deformation via Local Patch Meshing (NeurIPS 2025 · similarity 0.87)
- RigAnyFace: Scaling Neural Facial Mesh Auto-Rigging with Unlabeled Data (NeurIPS 2025 · similarity 0.86)
- SCULPT: Shape-Conditioned Unpaired Learning of Pose-dependent Clothed and Textured Human Meshes (CVPR 2024 · similarity 0.85)
- 4Deform: Neural Surface Deformation for Robust Shape Interpolation (CVPR 2025 · similarity 0.85)
- REACTO: Reconstructing Articulated Objects from a Single Video (CVPR 2024 · similarity 0.85)
- Implicit Neural Surface Deformation with Explicit Velocity Fields (ICLR 2025 · similarity 0.85)
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.
