Research map / 3D vision / Human pose estimation
Garment4D: Garment Reconstruction from Point Cloud Sequences
Fangzhou Hong, Liang Pan, Zhongang Cai, Ziwei Liu
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 displacement prediction on top of interpolated LBS (ablation) | Garment4D · CLOTH3D posed skirt | per-vertex L2 error (mm): 79.52 -> 49.39 | Improved |
| add displacement prediction on top of interpolated LBS (ablation) | Garment4D · CLOTH3D posed T-shirt | per-vertex L2 error (mm): 44.55 -> 37.83 | Improved |
| add hierarchical body surface encoder (ablation) | Garment4D · CLOTH3D posed garment | per-vertex L2 error (mm): -8.42 mm L2 error | Improved |
| add temporal transformer (ablation) | Garment4D · CLOTH3D posed garment | per-vertex L2 error (mm): -2.21 mm L2 error | Improved |
| add temporal transformer (ablation) | Garment4D · CLOTH3D posed garment | acceleration error (m/s^2): -5.575 m/s^2 | Improved |
| interpolate skinning weights from K=256 neighbors instead of nearest vertex (K=1) (ablation) | Garment4D · CLOTH3D posed garment | per-vertex L2 error (mm): -7.1 mm L2 error | Improved |
| replace adapted MGN (SMPL+D) with Garment4D | posed skirt reconstruction · CLOTH3D posed skirt | per-vertex L2 error (mm): 71.66 -> 49.39 | Improved |
| semantic-aware PCA encoder instead of PointNet++ | canonical garment estimation · CLOTH3D canonical T-shirt | per-vertex L2 error (mm): 41.05 -> 28.39 | Improved |
| increase point cloud incompleteness up to 50% | Garment4D · CLOTH3D skirt | reconstruction quality | No clear effect |
Closest papers by meaning
- Deep Fashion3D: A Dataset and Benchmark for 3D Garment Reconstruction from Single Images (ECCV 2020 · similarity 0.94)
- Spatio-Temporal Garment Reconstruction Using Diffusion Mapping via Pattern Coordinates (TPAMI 2026 · similarity 0.92)
- CLOTH4D: A Dataset for Clothed Human Reconstruction (CVPR 2023 · similarity 0.92)
- GaPT-DAR: Category-level Garments Pose Tracking via Integrated 2D Deformation and 3D Reconstruction (CVPR 2025 · similarity 0.91)
- VS: Reconstructing Clothed 3D Human from Single Image via Vertex Shift (CVPR 2024 · similarity 0.91)
- 4D-DRESS: A 4D Dataset of Real-World Human Clothing With Semantic Annotations (CVPR 2024 · similarity 0.90)
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.
