Research map / 3D vision / Face and shape
Disentangled Clothed Avatar Generation from Text Descriptions
Jionghao Wang, Yuan Liu, Zhiyang Dou, Zhengming Yu, Yongqing Liang, Cheng Lin, Rong Xie, Li Song, Xin Li, Wenping Wang
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 albedo smoothness loss with Phong shading model (ablation) | SO-SMPL · clothes albedo and animation | baked-in shadows and wrinkles (qualitative) | Improved |
| add OpenPose-based ControlNet guidance in body generation (ablation) | SO-SMPL Stage I · avatar generation | geometry and texture detail (qualitative) | Improved |
| use clothed-human guidance in addition to clothes-only guidance (ablation) | SO-SMPL Stage II · clothes generation | texture coherence (qualitative) | Improved |
| use clothes-only guidance in addition to clothed-human guidance (ablation) | SO-SMPL Stage II · clothes generation | skin color on clothes (qualitative) | Improved |
| add negative prompts such as skin, legs for clothes and loose clothes for body | SO-SMPL · body/clothes disentanglement | entanglement (qualitative) | Improved |
| disentangled body and clothes vs TADA on FID | TADA · A-pose avatars, 30 prompts | FID: 90.2 -> 84.9 | Improved |
| disentangled body and clothes vs TADA on CLIP score | TADA · A-pose avatars, 30 prompts | CLIP Score: 24.9 -> 28.4 | Improved |
Closest papers by meaning
- DAGSM: Disentangled Avatar Generation with GS-enhanced Mesh (CVPR 2025 · similarity 0.90)
- CtrlAvatar: Controllable Avatars Generation via Disentangled Invertible Networks (AAAI 2025 · similarity 0.87)
- SimAvatar: Simulation-Ready Avatars with Layered Hair and Clothing (CVPR 2025 · similarity 0.86)
- AvatarVerse: High-Quality & Stable 3D Avatar Creation from Text and Pose (AAAI 2024 · similarity 0.86)
- DreamAvatar: Text-and-Shape Guided 3D Human Avatar Generation via Diffusion Models (CVPR 2024 · similarity 0.86)
- MPMAvatar: Learning 3D Gaussian Avatars with Accurate and Robust Physics-Based Dynamics (NeurIPS 2025 · similarity 0.85)
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.
