Research map / 3D vision / Face and shape
Text to Layer-wise 3D Clothed Human Generation
Junting Dong, Qi Fang, Zehuan Huang, Xudong XU, Jingbo Wang, Sida Peng, Bo Dai
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 |
|---|---|---|---|
| model clothed human as layer-wise disentangled NeRFs instead of holistic single-stage model | TELA vs DreamWaltz · Text-to-3D clothed human generation | FID: 142.6 -> 125.9 | Improved |
| use disentangled layer-wise modeling instead of holistic DreamWaltz in user study | TELA · User study overall quality | preference (%): 71.46% | Improved |
| add transparency-based stratified composition instead of max-density fusion of layers (ablation) | TELA · Qualitative ablation (Figure 6) | layer penetration (qualitative) | Improved |
| add cloth-only SDS loss (dual SDS losses) (ablation) | TELA · Qualitative ablation (Figure 7) | cloth-body disentanglement (qualitative) | Improved |
| add 2D skeleton-conditioned ControlNet SDS for cloth generation composed with the body | TELA · Cloth generation vs DreamFusion/Magic3D/ProlificDreamer | multi-face problem (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.
- DreamWaltz — DreamWaltz: Make a Scene with Complex 3D Animatable Avatars (NeurIPS 2023) · better on 1 of 1 shared result
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
- HumanLiff: Layer-wise 3D Human Diffusion Model (IJCV 2025 · similarity 0.90)
- Design2Cloth: 3D Cloth Generation from 2D Masks (CVPR 2024 · similarity 0.90)
- DAGSM: Disentangled Avatar Generation with GS-enhanced Mesh (CVPR 2025 · similarity 0.90)
- Learning to Dress 3D People in Generative Clothing (CVPR 2020 · similarity 0.89)
- FreeCloth: Free-form Generation Enhances Challenging Clothed Human Modeling (CVPR 2025 · similarity 0.88)
- HumanRef: Single Image to 3D Human Generation via Reference-Guided Diffusion (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.
