Research map / Image generation / Editing and style transfer
OmniVTON: Training-Free Universal Virtual Try-On
Zhaotong Yang, Yuhui Li, Shengfeng He, Xinzhe Li, Yangyang Xu, Junyu Dong, Yong 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 |
|---|---|---|---|
| add Structured Garment Morphing (SGM) (ablation) | Base · VITON-HD | FID_u: 18.445 -> 13.303 | Improved |
| add Continuous Boundary Stitching (CBS) to SGM (ablation) | SGM variant (A) · VITON-HD | FID_u: 13.303 -> 9.799 | Improved |
| add CBS to SGM (ablation) | SGM variant (A) · VITON-HD | LPIPS_p: 0.177 -> 0.158 | Improved |
| add Spectral Pose Injection (SPI) to SGM+CBS (ablation) | SGM+CBS (B) · VITON-HD | FID_u: 9.799 -> 9.621 | Improved |
| add SPI to SGM+CBS (ablation) | SGM+CBS (B) · VITON-HD | SSIM_p: 0.824 -> 0.832 | Improved |
| add SPI alone to Base (ablation) | Base · VITON-HD | FID_u: 18.445 -> 13.148 | Improved |
| add semantic parsing (ablation) | OmniVTON · VITON-HD | FID_u: 13.705 -> 9.621 | Improved |
| add Ic-path attention modulation (ablation) | OmniVTON · VITON-HD | FID_u: 9.808 -> 9.621 | Improved |
| add high-frequency noise in SPI (ablation) | OmniVTON · VITON-HD | FID_u: 15.817 -> 9.621 | Improved |
| use SPI instead of average noise (ablation) | OmniVTON · VITON-HD | FID_u: 12.402 -> 9.621 | Improved |
| use average noise instead of SPI (ablation) | OmniVTON · VITON-HD | SSIM_p: 0.849 vs 0.832 | Hurt |
| use SPI instead of ControlNet (ablation) | OmniVTON · VITON-HD | FID_u: 10.873 -> 9.621 | Improved |
Later papers that compared with this method
2 later accepted papers report OmniVTON as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- PG-VTON: Single-Pass Training-Free Virtual Try-On via Patch-Guided Reference Alignment (CVPR 2026 · better on 8 of 8 shared results)
- RefTon: Reference person shot assist virtual Try-on (CVPR 2026 · better on 2 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
- MV-VTON: Multi-View Virtual Try-On with Diffusion Models (AAAI 2025 · similarity 0.90)
- BooW-VTON: Boosting In-the-Wild Virtual Try-On via Mask-Free Pseudo Data Training (CVPR 2025 · similarity 0.90)
- OmniTry: Virtual Try-On Anything without Masks (NeurIPS 2025 · similarity 0.90)
- OpenVTON-Bench: A Large-Scale High-Resolution Benchmark for Controllable Virtual Try-On Evaluation (NeurIPS 2026 · similarity 0.90)
- Robust-MVTON: Learning Cross-Pose Feature Alignment and Fusion for Robust Multi-View Virtual Try-On (CVPR 2025 · similarity 0.90)
- Incorporating Visual Correspondence into Diffusion Model for Virtual Try-On (ICLR 2025 · similarity 0.89)
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.
