Research map / Image generation / Editing and style transfer
Do Not Mask What You Do Not Need to Mask: a Parser-Free Virtual Try-On
Thibaut Issenhuth, Jérémie Mary, Clément Calauzènes
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 agnostic person representation of CP-VTON with parser-free T-WUTON input | CP-VTON · Virtual try-on test set | FID: 37.237 -> 16.843 | Improved |
| train with teacher-student parser-free pipeline (T-WUTON) | CP-VTON on p*_t-wuton · Virtual try-on test set | FID: 16.843 -> 9.877 | Improved |
| distill teacher into parser-free student (S-WUTON) | T-WUTON · Virtual try-on test set | FID: 9.877 -> 7.927 | Improved |
| distill into student removing parser and pose at inference | T-WUTON · Runtime (V100) | total runtime (ms): 181ms -> 13ms | Improved |
| add adversarial loss to student (ablation) | S-WUTON · Virtual try-on test set | FID: 12.620 -> 7.927 | Improved |
| add adversarial loss to student (ablation) | S-WUTON · Virtual try-on test set | IS: 2.912 -> 3.154 | Improved |
| add unpaired adversarial loss (ablation) | T-WUTON · Virtual try-on test set | FID: 13.020 -> 9.877 | Improved |
| add unpaired adversarial loss (ablation) | T-WUTON · Virtual try-on test set | IS: 2.729 -> 3.114 | Improved |
| add unpaired adversarial loss (ablation) | T-WUTON · Virtual try-on test set | LPIPS: 0.107 -> 0.101 | Improved |
| train geometric matcher end-to-end with synthesis loss (ablation) | T-WUTON · Virtual try-on test set | FID: 11.125 -> 9.877 | Improved |
| train geometric matcher end-to-end (ablation) | T-WUTON · Virtual try-on test set | LPIPS: 0.112 -> 0.101 | Improved |
| train geometric matcher end-to-end (ablation) | T-WUTON · Virtual try-on test set | IS: 3.102 -> 3.114 | No clear effect |
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.
- VTNFP — VTNFP: An Image-Based Virtual Try-On Network With Body and Clothing Feature Preservation (ICCV 2019) · 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
- BooW-VTON: Boosting In-the-Wild Virtual Try-On via Mask-Free Pseudo Data Training (CVPR 2025 · similarity 0.89)
- Texture-Preserving Diffusion Models for High-Fidelity Virtual Try-On (CVPR 2024 · similarity 0.89)
- M&M VTO: Multi-Garment Virtual Try-On and Editing (CVPR 2024 · similarity 0.88)
- IMAGDressing-v1: Customizable Virtual Dressing (AAAI 2025 · similarity 0.87)
- CycleVTON: A Cycle Mapping Framework for Parser-Free Virtual Try-On (AAAI 2024 · similarity 0.86)
- Enhancing Virtual Try-On with Synthetic Pairs and Error-Aware Noise Scheduling (CVPR 2025 · similarity 0.86)
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.
