Research map / 3D vision / Face and shape
CLOTH4D: A Dataset for Clothed Human Reconstruction
Xingxing Zou, Xintong Han, Waikeung Wong
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 |
|---|---|---|---|
| Retrain PIFu on CLOTH4D rather than its original scan training data | PIFu · CLOTH4D test | Chamfer ↓: 3.578 -> 2.412 | Improved |
| Retrain ICON on CLOTH4D rather than its original scan training data | ICON · CLOTH4D test | Chamfer ↓: 4.196 -> 3.499 | Improved |
| Retrain PIFu on CLOTH4D rather than its original scan training data | PIFu · CAPE test | Chamfer ↓: 4.204 -> 4.381 | Hurt |
| Retrain ICON on CLOTH4D rather than its original scan training data | ICON · CAPE test | Chamfer ↓: 3.962 -> 3.544 | Hurt |
| Use ground-truth SMPL fits instead of estimated SMPL | ICON · CLOTH4D test | Chamfer ↓: 4.196 -> 1.631 | Improved |
| Use ground-truth SMPL fits instead of estimated SMPL | PaMIR · CLOTH4D test | Chamfer ↓: 4.157 -> 2.487 | Improved |
| Add a temporal term penalizing Chamfer distance between successive frames (ablation) | PIFuclo · CLOTH4D test | Chamferddt ↓: 0.157→0.123 | Improved |
| Add a temporal term penalizing Chamfer distance between successive frames (ablation) | PIFuclo · CLOTH4D test | Chamferdtd ↓: 0.546→0.454 | Improved |
| Use CLOTH4D-trained models instead of original models | PIFu and PaMIR · CLOTH4D test | reconstruction quality: PIFu P2S: 3.911 -> 2.793; PaMIR P2S: 3.827 -> 5.037 | Mixed |
| Use ground-truth SMPL fits instead of estimated SMPL | ICON · CLOTH4D test | Normalsddt ↓: 0.013 -> 0.030 | Hurt |
Closest papers by meaning
- 4D-DRESS: A 4D Dataset of Real-World Human Clothing With Semantic Annotations (CVPR 2024 · similarity 0.92)
- DeClotH: Decomposable 3D Cloth and Human Body Reconstruction from a Single Image (CVPR 2025 · similarity 0.89)
- DLCA-Recon: Dynamic Loose Clothing Avatar Reconstruction from Monocular Videos (AAAI 2024 · similarity 0.89)
- FreeCloth: Free-form Generation Enhances Challenging Clothed Human Modeling (CVPR 2025 · similarity 0.89)
- VS: Reconstructing Clothed 3D Human from Single Image via Vertex Shift (CVPR 2024 · similarity 0.89)
- D^3-Human: Dynamic Disentangled Digital Human from Monocular Video (CVPR 2025 · similarity 0.89)
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.
