Research map / Image generation / Editing and style transfer
IMAGGarment+: Efficient Attribute-Wise Diffusion for Garment Generation
Jian Yu, Fei Shen, Cong Wang, Yanpeng Sun, Hao Tang, Qin Guo, Xiaoyu Du
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 |
|---|---|---|---|
| replace AFE (attribute-wise LoRA extractor) with IP-Adapter (ablation) | IMAGGarment+ · GarmentBench | FID: 77.92 -> 16.16 | Improved |
| add attribute-adaptive attention instead of element-wise addition (ablation) | IMAGGarment+ · GarmentBench | FID: 25.35 -> 16.16 | Improved |
| add layer-wise injection strategy (ablation) | IMAGGarment+ · GarmentBench | CSS: 61.22 -> 38.30 | Improved |
| add layer-wise injection strategy (ablation) | IMAGGarment+ · GarmentBench | LLA: 0.89 -> 0.90 | No clear effect |
| inject silhouette into first upsampling layer U1 (ablation) | IMAGGarment+ · GarmentBench | FID | Improved |
| inject color into second upsampling layer U2 (ablation) | IMAGGarment+ · GarmentBench | FID | Improved |
| increase logo injection strength lambda_l (ablation) | IMAGGarment+ · GarmentBench | logo completeness | Improved |
| replace multi-adapter stacking (ControlNet) with AFE+AA | IMAGGarment+ · GarmentBench | FID: 55.20 -> 16.16 | Improved |
| compare with IMAGGarment-1 | IMAGGarment+ · GarmentBench | CSS: 57.29 -> 38.30 | Improved |
| compare with IMAGGarment-1 | IMAGGarment+ · GarmentBench | FID: 16.51 -> 16.16 | No clear effect |
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.
- DreamFit — DreamFit: Garment-Centric Human Generation via a Lightweight Anything-Dressing Encoder (AAAI 2025) · better on 4 of 4 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
- AnyDressing: Customizable Multi-Garment Virtual Dressing via Latent Diffusion Models (CVPR 2025 · similarity 0.90)
- IMAGDressing-v1: Customizable Virtual Dressing (AAAI 2025 · similarity 0.89)
- DreamFit: Garment-Centric Human Generation via a Lightweight Anything-Dressing Encoder (AAAI 2025 · similarity 0.89)
- ITA-MDT: Image-Timestep-Adaptive Masked Diffusion Transformer Framework for Image-Based Virtual Try-On (CVPR 2025 · similarity 0.88)
- Cascaded Diffusion Models for Virtual Try-On: Improving Control and Resolution (AAAI 2025 · similarity 0.88)
- Texture-Preserving Diffusion Models for High-Fidelity Virtual Try-On (CVPR 2024 · 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.
