Research map / 3D vision / Face and shape
Towards High-Quality 3D Motion Transfer with Realistic Apparel Animation
Rong Wang, Wei Mao, Changsheng Lu, HONGDONG LI
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 |
|---|---|---|---|
| add explicit apparel deformation module on top of body module (ablation) | motion transfer pipeline · MMDMC test set | PMD_a (cm): 5.42 -> 2.15 | Improved |
| add apparel module without joint refinement (ablation) | motion transfer pipeline · MMDMC test set | ELS: 0.82 -> 0.85 | No clear effect |
| add joint refinement module (ablation) | motion transfer pipeline · MMDMC test set | ELS: 0.85 -> 0.94 | Improved |
| provide ground truth apparel mask instead of predicted segmentation (ablation) | Full Model · MMDMC test set | PMD (cm): 1.08 -> 1.02 | Improved |
| add geodesic attention instead of no geodesic prior (ablation) | body deformation module · MMDMC (apparel physics disabled) | PMD (cm): 1.35 -> 1.14 | Improved |
| learned attention over geodesic distances instead of sorting joints by raw geodesic distance (ablation) | body deformation module · MMDMC (apparel physics disabled) | PMD (cm): 1.27 -> 1.14 | Improved |
| model apparel with learned displacement field conditioned on history instead of LBS with body skinning | NBS/SPT baselines · MMDMC test set | PMD_a (cm): 6.62 -> 1.91 | Improved |
Closest papers by meaning
- Learning 3D Garment Animation from Trajectories of A Piece of Cloth (NeurIPS 2024 · similarity 0.89)
- DeePSD: Automatic Deep Skinning and Pose Space Deformation for 3D Garment Animation (ICCV 2021 · similarity 0.89)
- High-Fidelity Neural Human Motion Transfer From Monocular Video (CVPR 2021 · similarity 0.88)
- Garment Recovery with Shape and Deformation Priors (CVPR 2024 · similarity 0.87)
- FreeCloth: Free-form Generation Enhances Challenging Clothed Human Modeling (CVPR 2025 · similarity 0.87)
- DLCA-Recon: Dynamic Loose Clothing Avatar Reconstruction from Monocular Videos (AAAI 2024 · 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.
