Research map / Image generation / Text-to-image diffusion
FashionMAC: Deformation-Free Fashion Image Generation with Fine-Grained Model Appearance Customization
Rong Zhang, Jinxiao Li, Jingnan Wang, Zhiwen Zuo, Jianfeng Dong, Wei Li, Chi Wang, Weiwei Xu, Xun 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 chained mask injection (CMI) (ablation) | FashionMAC · VITON-HD, with text prompts guidance | FID: 14.91 -> 13.68 | Improved |
| add chained mask injection (CMI) (ablation) | FashionMAC · VITON-HD, with text prompts guidance | CLIP-t: 0.221 -> 0.231 | Improved |
| add region-adaptive decoupled attention (RADA) on top of CMI removal (ablation) | FashionMAC · VITON-HD, with text prompts guidance | FID: 15.21 -> 14.91 | Improved |
| add RADA on top of CMI removal (ablation) | FashionMAC · VITON-HD, with text prompts guidance | KID: 0.0077 -> 0.0073 | Improved |
| add RADA on top of CMI removal (ablation) | FashionMAC · VITON-HD, with text prompts guidance | CLIP-t: 0.222 -> 0.221 | No clear effect |
| outpaint dressed garment without deformation vs deformation-based baselines | FashionMAC · VITON-HD, with facial image guidance | MP-LPIPS: 0.083 -> 0.055 (vs IMAGDressing) | Improved |
| outpaint dressed garment without deformation vs deformation-based baselines | FashionMAC · VITON-HD, with facial image guidance | FID: 29.34 -> 14.89 (vs IMAGDressing) | Improved |
Closest papers by meaning
- Controllable Human Image Generation with Personalized Multi-Garments (CVPR 2025 · similarity 0.89)
- FashionR2R: Texture-preserving Rendered-to-Real Image Translation with Diffusion Models (NeurIPS 2024 · similarity 0.89)
- AnyDressing: Customizable Multi-Garment Virtual Dressing via Latent Diffusion Models (CVPR 2025 · similarity 0.89)
- FashionTailor: Controllable Clothing Editing for Human Images with Appearance Preserving (AAAI 2025 · similarity 0.89)
- Cascaded Diffusion Models for Virtual Try-On: Improving Control and Resolution (AAAI 2025 · similarity 0.88)
- FreeCloth: Free-form Generation Enhances Challenging Clothed Human Modeling (CVPR 2025 · similarity 0.88)
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.
