Research map / 3D vision / Face and shape
The Power of Points for Modeling Humans in Clothing
Qianli Ma, Jinlong Yang, Siyu Tang, Michael J. Black
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 |
|---|---|---|---|
| train one cross-outfit model on all outfits instead of per-outfit models (ablation) | POP · CAPE | Chamfer-L2 mean: 0.639 -> 0.592 | Improved |
| train one cross-outfit model on all outfits instead of per-outfit models (ablation) | POP · CAPE | Normal diff. mean: 1.146 -> 1.115 | Improved |
| train one cross-outfit model on all outfits instead of per-outfit models (ablation) | POP · ReSynth | Chamfer-L2 mean: 1.356 -> 1.366 | No clear effect |
| replace patch-based SCALE with dense continuous-feature point cloud (per-outfit) | SCALE · CAPE | Chamfer-L2 mean: 0.721 -> 0.639 | Improved |
| replace patch-based SCALE with dense continuous-feature point cloud (per-outfit) | SCALE · ReSynth | Chamfer-L2 mean: 1.491 -> 1.356 | Improved |
| replace implicit NASA with POP (per-outfit) | NASA · CAPE | Chamfer-L2 mean: 6.087 -> 0.639 | Improved |
| train with half of the data per outfit (ablation) | POP cross-outfit · CAPE | Chamfer-L2 mean: 0.592 -> 0.598 | Hurt |
| train with a quarter of the data per outfit (ablation) | POP cross-outfit · CAPE | Chamfer-L2 mean: 0.592 -> 0.621 | Hurt |
| train with one eighth of the data per outfit (ablation) | POP cross-outfit · CAPE | Chamfer-L2 mean: 0.592 -> 0.662 | Hurt |
| train with one eighth of the data per outfit (ablation) | POP cross-outfit · ReSynth | Chamfer-L2 mean: 1.366 -> 1.490 | Hurt |
| use POP rather than SCALE judged by human raters | SCALE · CAPE visual quality | user preference (%): 89.8% vs 10.2% | Improved |
| use POP rather than SCALE judged by human raters | SCALE · ReSynth visual quality | user preference (%): 84.8% vs 15.2% | Improved |
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.
- SCALE — SCALE: Modeling Clothed Humans with a Surface Codec of Articulated Local Elements (CVPR 2021) · better on 6 of 6 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
- Point-Based Modeling of Human Clothing (ICCV 2021 · similarity 0.95)
- SCALE: Modeling Clothed Humans with a Surface Codec of Articulated Local Elements (CVPR 2021 · similarity 0.94)
- CloSET: Modeling Clothed Humans on Continuous Surface With Explicit Template Decomposition (CVPR 2023 · similarity 0.93)
- Learning to Dress 3D People in Generative Clothing (CVPR 2020 · similarity 0.92)
- SCULPT: Shape-Conditioned Unpaired Learning of Pose-dependent Clothed and Textured Human Meshes (CVPR 2024 · similarity 0.89)
- FreeCloth: Free-form Generation Enhances Challenging Clothed Human Modeling (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.
