Research map / 3D vision / Face and shape
Towards Multi-Layered 3D Garments Animation
Yidi Shao, Chen Change Loy, Bo Dai
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 Rotation Equivalent Transformation (ablation) | LayersNet with body collision loss · D-LAYERS | garment-to-body collision rate (%): 9.51 -> 2.72 | Improved |
| add Rotation Equivalent Transformation (ablation) | LayersNet with body collision loss · D-LAYERS | Euclidean error (mm): 446.3 -> 449.2 | No clear effect |
| add RET to body collision loss (ablation) | LayersNet · D-LAYERS | garment-to-garment collision rate (%): 3.10 -> 5.21 | Hurt |
| add garment-to-body collision loss (ablation) | LayersNet vanilla · D-LAYERS | Euclidean error (mm): 472.8 -> 446.3 | Improved |
| add garment-to-garment collision loss (ablation) | LayersNet with RET · D-LAYERS | garment-to-garment collision rate (%): 5.21 -> 2.62 | Improved |
| add garment-to-garment collision loss (ablation) | LayersNet with RET · D-LAYERS | garment-to-body collision rate (%): 2.72 -> 4.28 | Hurt |
| add collision loss to DeePSD | DeePSD · D-LAYERS general | Euclidean error (mm): 1049.8 -> 1563.4 | Hurt |
| add collision loss to LayersNet | LayersNet · D-LAYERS general | Euclidean error (mm): 472.8 -> 467.2 | Improved |
| train on multi-layered garments instead of inner only | DeePSD · D-LAYERS split T | Euclidean error (mm): 225.3 -> 1072.6 | Hurt |
| add strong wind | DeePSD and LayersNet on inner garments · D-LAYERS splits T vs T+W | Euclidean error (mm): DeePSD 225.3 -> 239.5; LayersNet 220.0 -> 258.0 | Mixed |
| use garment-specific MGNet instead of particle-based model | inner-garment animation · D-LAYERS split T | Euclidean error (mm): 220.0 -> 5219.2 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- DeePSD — DeePSD: Automatic Deep Skinning and Pose Space Deformation for 3D Garment Animation (ICCV 2021) · better on 8 of 9 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Learning 3D Garment Animation from Trajectories of A Piece of Cloth (NeurIPS 2024 · similarity 0.91)
- GarNet: A Two-Stream Network for Fast and Accurate 3D Cloth Draping (ICCV 2019 · similarity 0.88)
- Self-Supervised Collision Handling via Generative 3D Garment Models for Virtual Try-On (CVPR 2021 · similarity 0.88)
- MPMAvatar: Learning 3D Gaussian Avatars with Accurate and Robust Physics-Based Dynamics (NeurIPS 2025 · similarity 0.88)
- GarmentLab: A Unified Simulation and Benchmark for Garment Manipulation (NeurIPS 2024 · similarity 0.88)
- DexGarmentLab: Dexterous Garment Manipulation Environment with Generalizable Policy (NeurIPS 2025 · similarity 0.87)
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.
