Research map / Image generation / Editing and style transfer
Improving Virtual Try-On with Garment-focused Diffusion Models
Siqi Wan, Yehao Li, Jingwen Chen, Yingwei Pan, Ting Yao, Yang Cao, Tao Mei
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 garment-focused adapter (CLIP + VAE appearance priors with garment mask attention) (ablation) | Base SD inpainting · VITON-HD | SSIM: 0.809 -> 0.898 | Improved |
| Add appearance loss (DISTS + Sobel high-frequency) to Base (ablation) | Base SD inpainting · VITON-HD | SSIM: 0.809 -> 0.829 | Improved |
| Add appearance loss on top of GFA (ablation) | Base+GFA · VITON-HD | FID_u: 8.21 -> 7.89 | Improved |
| Add appearance loss on top of GFA (ablation) | Base+GFA · VITON-HD | KID_p: 0.047 -> 0.019 | Improved |
| Use garment-focused GarDiff instead of best prior diffusion VTON (DCI-VTON) | virtual try-on · VITON-HD | SSIM: 0.896 -> 0.912 | Improved |
| GarDiff vs DCI-VTON on DressCode upper-body unpaired FID | virtual try-on · DressCode upper-body (unpaired) | FID: 10.82 vs 11.32 | Hurt |
| Feed both unwarped garment and warped garment priors to the diffusion model (ablation) | GarDiff · VITON-HD (qualitative) | visual quality | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- GP-VTON — GP-VTON: Towards General Purpose Virtual Try-On via Collaborative Local-Flow Global-Parsing Learning (CVPR 2023) · better on 1 of 2 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
- Incorporating Visual Correspondence into Diffusion Model for Virtual Try-On (ICLR 2025 · similarity 0.95)
- Texture-Preserving Diffusion Models for High-Fidelity Virtual Try-On (CVPR 2024 · similarity 0.93)
- Cascaded Diffusion Models for Virtual Try-On: Improving Control and Resolution (AAAI 2025 · similarity 0.93)
- MV-VTON: Multi-View Virtual Try-On with Diffusion Models (AAAI 2025 · similarity 0.91)
- ITA-MDT: Image-Timestep-Adaptive Masked Diffusion Transformer Framework for Image-Based Virtual Try-On (CVPR 2025 · similarity 0.91)
- CatVTON: Concatenation Is All You Need for Virtual Try-On with Diffusion Models (ICLR 2025 · similarity 0.90)
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.
