Research map / 3D vision / Face and shape
SCANimate: Weakly Supervised Learning of Skinned Clothed Avatar Networks
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 learned canonicalization with cycle consistency instead of nearest-neighbor skinning weights (ablation) | SCANimate · CAPE Int. | scan-to-mesh distance (cm): 1.25 -> 0.570 | Helped |
| Use learned canonicalization with cycle consistency instead of interpolated k-nearest-neighbor weights (ablation) | SCANimate · CAPE Int. | scan-to-mesh distance (cm): 1.25 -> 0.570 | Helped |
| Use local pose conditioning instead of global pose conditioning (ablation) | SCANimate · CAPE Int., 5% training data | scan-to-mesh distance (cm): 2.38 -> 0.732 | Helped |
| Use local pose conditioning instead of global pose conditioning (ablation) | SCANimate · CAPE Ex., 5% training data | plausibility score (image): 0.192 -> 0.359 | Helped |
| Use local rather than global pose conditioning (ablation) | SCANimate · CAPE Int. and Ex. | scan-to-mesh distance (cm): 0.768 vs. 0.570; 0.786 vs. 0.663; 1.54 vs. 0.699; 2.38 vs. 0.732 | Mixed |
| Replace SCANimate with CAPE's registered fixed-topology model | SCANimate · CAPE Int. | scan-to-mesh distance (cm): 0.970 -> 0.570 | Helped |
| Replace SCANimate with NASA's articulated implicit functions | SCANimate · CAPE Int. | scan-to-mesh distance (cm): 1.12 -> 0.570 | Helped |
Closest papers by meaning
- SCULPT: Shape-Conditioned Unpaired Learning of Pose-dependent Clothed and Textured Human Meshes (CVPR 2024 · similarity 0.90)
- FreeCloth: Free-form Generation Enhances Challenging Clothed Human Modeling (CVPR 2025 · similarity 0.89)
- FRESA: Feedforward Reconstruction of Personalized Skinned Avatars from Few Images (CVPR 2025 · similarity 0.89)
- 3DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splatting (CVPR 2024 · similarity 0.88)
- CtrlAvatar: Controllable Avatars Generation via Disentangled Invertible Networks (AAAI 2025 · similarity 0.88)
- Pose Modulated Avatars from Video (ICLR 2024 · similarity 0.88)
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.