Research map / 3D vision / Face and shape
Learning Implicit Templates for Point-Based Clothed Human Modeling
Siyou Lin, Hongwen Zhang, Zerong Zheng, Ruizhi Shao, Yebin 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 |
|---|---|---|---|
| use point-based representation (FITE, POP) instead of implicit methods | FITE · CAPE and ReSynth interpolation | d_cham (x1e5): SNARF 2.426 -> FITE 1.355 (Felice 004 long dress) | Improved |
| learn implicit outfit template instead of fixed minimal body template | FITE vs POP · ReSynth Carla 004 long pants | d_cham (x1e5): 0.485 -> 0.299 | Improved |
| learn implicit outfit template instead of fixed minimal body template | FITE vs POP · ReSynth Felice 004 long dress | d_cham (x1e5): 1.718 -> 1.355 | Improved |
| learn implicit outfit template instead of fixed minimal body template | FITE vs POP · CAPE 03375 blazerlong | d_cham (x1e5): 0.252 -> 0.274 | Hurt |
| learn implicit outfit template instead of fixed minimal body template | FITE vs POP · ReSynth Christine 027 short dress | d_cham (x1e5): 0.421 -> 0.455 | Hurt |
| cross-outfit training (FITE vs outfit-specific FITE-OS) (ablation) | FITE · ReSynth Felice 004 long dress | d_cham (x1e5): 1.805 -> 1.355 | Improved |
| cross-outfit training (FITE vs outfit-specific FITE-OS) (ablation) | FITE · CAPE tight outfits | d_cham (x1e5): 0.041 -> 0.042 (00096), 0.074 -> 0.076 (00215) | No clear effect |
| FITE instead of POP, user preference on point clouds | FITE · Extrapolation user study | vote share (%): 24.58 -> 75.42 | Improved |
| FITE instead of POP, user preference on meshes | FITE · Extrapolation user study | vote share (%): 40.63 -> 59.37 | Improved |
| fix diffused skinning weights instead of jointly learning skinning field (ablation) | FITE stage one · template training | qualitative | 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.
- SCANimate — SCANimate: Weakly Supervised Learning of Skinned Clothed Avatar Networks (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
- CloSET: Modeling Clothed Humans on Continuous Surface With Explicit Template Decomposition (CVPR 2023 · similarity 0.92)
- The Power of Points for Modeling Humans in Clothing (ICCV 2021 · similarity 0.92)
- SCANimate: Weakly Supervised Learning of Skinned Clothed Avatar Networks (CVPR 2021 · similarity 0.91)
- FreeCloth: Free-form Generation Enhances Challenging Clothed Human Modeling (CVPR 2025 · similarity 0.90)
- Point-Based Modeling of Human Clothing (ICCV 2021 · similarity 0.90)
- SCULPT: Shape-Conditioned Unpaired Learning of Pose-dependent Clothed and Textured Human Meshes (CVPR 2024 · similarity 0.87)
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.
