Research map / Image generation / Text-to-image diffusion
DiffCloth: Diffusion Based Garment Synthesis and Manipulation via Structural Cross-modal Semantic Alignment
Xujie Zhang, Binbin Yang, Michael C. Kampffmeyer, Wenqing Zhang, Shiyue Zhang, Guansong Lu, Liang Lin, Hang Xu, Xiaodan Liang
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 structural semantic consensus guidance (Hungarian matching loss) (ablation) | Stable Diffusion · CM-Fashion | CLIPScore: 0.8169 -> 0.8821 | Improved |
| add semantic-bundled cross-attention (ablation) | Stable Diffusion · CM-Fashion | FID: 9.475 -> 9.221 | Improved |
| add semantic-bundled cross-attention (ablation) | Stable Diffusion · CM-Fashion | IS: 24.59 -> 26.69 | Improved |
| combine both guidance components (ablation) | DiffCloth · CM-Fashion | FID / IS / CLIPScore: 9.475 -> 9.201 FID; 24.59 -> 26.95 IS; 0.8169 -> 0.8974 CLIPScore | Improved |
| add region consistency blended mask in garment manipulation (ablation) | DiffCloth manipulation · CM-Fashion manipulation | preservation of irrelevant regions | Improved |
| DiffCloth versus generic diffusion baselines on FID | DiffCloth · CM-Fashion | FID: 9.238 (StructureDiffusion) vs 9.201 | No clear effect |
| DiffCloth versus baselines in human evaluation | DiffCloth · human evaluation of synthesis and manipulation | preference | Improved |
Later papers that compared with this method
2 later accepted papers report DiffCloth as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- IMAGGarment+: Efficient Attribute-Wise Diffusion for Garment Generation (AAAI 2026 · better on 4 of 4 shared results)
- GarmentAligner: Text-to-Garment Generation via Retrieval-augmented Multi-level Corrections (ECCV 2024 · better on 2 of 2 shared results)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- TediGAN — TediGAN: Text-Guided Diverse Face Image Generation and Manipulation (CVPR 2021) · better on 1 of 1 shared result
- Cogview — CogView: Mastering Text-to-Image Generation via Transformers (NeurIPS 2021) · 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
- FashionTailor: Controllable Clothing Editing for Human Images with Appearance Preserving (AAAI 2025 · similarity 0.90)
- AnyDressing: Customizable Multi-Garment Virtual Dressing via Latent Diffusion Models (CVPR 2025 · similarity 0.88)
- TexFit: Text-Driven Fashion Image Editing with Diffusion Models (AAAI 2024 · similarity 0.88)
- HieraFashDiff: Hierarchical Fashion Design with Multi-stage Diffusion Models (AAAI 2025 · similarity 0.88)
- DreamFit: Garment-Centric Human Generation via a Lightweight Anything-Dressing Encoder (AAAI 2025 · similarity 0.87)
- AIpparel: A Multimodal Foundation Model for Digital Garments (CVPR 2025 · 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.
