Research map / 3D vision / Face and shape
Skinned Motion Retargeting With Residual Perception of Motion Semantics & Geometry
Read the paperCheck 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 skeleton-aware motion-semantic adjustment to copied motion (ablation) | R²ET without geometry module · Mixamo | MSE: 0.267 -> 0.297 | Helped |
| Add the shape-aware module and balancing gate (ablation) | R²ET without geometry module · Mixamo | penetration rate (%): 9.09 -> 5.94 | Helped |
| Add the shape-aware module and balancing gate (ablation) | R²ET without geometry module · Mixamo | self-contact distance (cm): 4.93 -> 3.57 | Helped |
| Add the balancing gate to combine skeleton- and shape-level adjustments (ablation) | R²ET without balancing gate · Mixamo | self-contact distance (cm): 5.31 -> 3.57 | Helped |
| Add the balancing gate to combine skeleton- and shape-level adjustments (ablation) | R²ET without balancing gate · Mixamo | penetration rate (%): 4.68 -> 5.94 | Hurt |
| Add the balancing gate to combine skeleton- and shape-level adjustments (ablation) | R²ET without balancing gate · Mixamo | MSE: 0.378 -> 0.318 | Hurt |
| Use residual retargeting instead of full-motion mapping | Motion retargeting · Mixamo | temporal smoothness | Helped |
Closest papers by meaning
- Semantics-aware Motion Retargeting with Vision-Language Models (CVPR 2024 · similarity 0.89)
- Skinned Motion Retargeting with Dense Geometric Interaction Perception (NeurIPS 2024 · similarity 0.87)
- Restage4D: Reanimating Deformable 3D Reconstruction from a Single Video (NeurIPS 2025 · similarity 0.85)
- Motion4D: Learning 3D-Consistent Motion and Semantics for 4D Scene Understanding (NeurIPS 2025 · similarity 0.84)
- SAMoR: Motion Modelling for Articulated Objects of Any Skeleton and Topology (NeurIPS 2026 · similarity 0.84)
- REACTO: Reconstructing Articulated Objects from a Single Video (CVPR 2024 · similarity 0.83)
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.