Research map / 3D vision / Face and shape
CLOTH3D: Clothed 3D Humans
Hugo Bertiche, Meysam Madadi, Sergio Escalera
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 normals loss (ablation) | GCVAE · CLOTH3D static | surface error (mm): 22.8 -> 14.3 | Improved |
| add normals loss (ablation) | GCVAE · CLOTH3D static | KL loss: 0.5966 -> 0.9820 | Hurt |
| add mask prediction (ablation) | GCVAE · CLOTH3D static | surface error (mm): 92.7 -> 14.3 | Improved |
| add mask prediction (ablation) | GCVAE · CLOTH3D static | normals error (rad): 1.19 -> 1.04 | Improved |
| add collision loss (ablation) | GCVAE · CLOTH3D static | surface error (mm): 14.7 -> 14.3 | Improved |
| add collision loss (ablation) | GCVAE · CLOTH3D static | normals error (rad): 1.02 -> 1.04 | Hurt |
| add conditional-variable regression (CVAR) from encoder (ablation) | GCVAE · CLOTH3D static | KL loss: 1.1009 -> 0.9820 | Hurt |
| add conditional-variable regression (CVAR) from encoder (ablation) | GCVAE · CLOTH3D static | surface error (mm): 14.8 -> 14.3 | No clear effect |
| use proposed pooling instead of default mesh simplification (ablation) | GCVAE · CLOTH3D static | mask IoU: 0.9390 -> 0.9518 | Improved |
| use proposed pooling instead of default mesh simplification (ablation) | GCVAE · CLOTH3D static | surface error (mm): 14.9 -> 14.3 | Improved |
| condition on four frames instead of one frame (ablation) | DVAE · CLOTH3D dynamic | surface error (mm): 29.0 -> 26.1 | Improved |
| condition on four frames instead of one frame (ablation) | DVAE · CLOTH3D dynamic | normals error (rad): 1.10 -> 1.08 | Improved |
Closest papers by meaning
- Generating Datasets of 3D Garments with Sewing Patterns (NeurIPS 2021 · similarity 0.90)
- GarmentCodeData: A Dataset of 3D Made-to-Measure Garments With Sewing Patterns (ECCV 2024 · similarity 0.90)
- CLOTH4D: A Dataset for Clothed Human Reconstruction (CVPR 2023 · similarity 0.90)
- Design2Cloth: 3D Cloth Generation from 2D Masks (CVPR 2024 · similarity 0.89)
- SCULPT: Shape-Conditioned Unpaired Learning of Pose-dependent Clothed and Textured Human Meshes (CVPR 2024 · similarity 0.88)
- DressWild: Feed-Forward Pose-Agnostic Garment Sewing Pattern Generation from In-the-Wild Images (NeurIPS 2026 · 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.
