Research map / 3D vision / Human pose estimation
Cloth2Body: Generating 3D Human Body Mesh from 2D Clothing
Lu Dai, Liqian Ma, Shenhan Qian, Hao Liu, Ziwei Liu, Hui Xiong
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 |
|---|---|---|---|
| use kinematics-aware pose estimation with physics-informed shape instead of HybrIK/HMR/PARE regression | Cloth2Body · DeepFashion2-SMPL | 2D-KPE-C: 27.46 -> 23.53 vs HybrIK | Improved |
| estimate shape from landmarks and joints as proxy instead of direct beta regression | Cloth2Body · DeepFashion2-SMPL shape | Chest error (mm): 20.0 -> 18.7 vs HMR | Improved |
| add adaptive depth to HybrIK (ablation) | HybrIK · DeepFashion2-SMPL | 2D-KPE-C: 31.58 -> 27.46 | Improved |
| add adaptive depth module to Cloth2Body (ablation) | Cloth2Body · DeepFashion2-SMPL | 2D-KPE-C: 23.53 -> 25.72 listed as Ours vs Ours-Ada | Improved |
| add predicted joints image input to shape estimation (ablation) | Landmark2Shape · DeepFashion2-SMPL | MPJPE-C: 63.67 -> 62.76 | Improved |
| add cloth landmark image input to shape estimation (ablation) | Landmark2Shape · DeepFashion2-SMPL | MPJPE-C: 62.76 -> 62.35 | Improved |
| add cloth landmark image input to shape estimation (ablation) | Landmark2Shape · DeepFashion2-SMPL | 2D-KPE-C: 23.56 -> 23.53 | No clear effect |
Closest papers by meaning
- 3DPeople: Modeling the Geometry of Dressed Humans (ICCV 2019 · similarity 0.92)
- Deep Fashion3D: A Dataset and Benchmark for 3D Garment Reconstruction from Single Images (ECCV 2020 · similarity 0.91)
- Detailed, Accurate, Human Shape Estimation From Clothed 3D Scan Sequences (CVPR 2017 · similarity 0.91)
- SCALE: Modeling Clothed Humans with a Surface Codec of Articulated Local Elements (CVPR 2021 · similarity 0.91)
- DeClotH: Decomposable 3D Cloth and Human Body Reconstruction from a Single Image (CVPR 2025 · similarity 0.90)
- VS: Reconstructing Clothed 3D Human from Single Image via Vertex Shift (CVPR 2024 · 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.
