Research map / Image generation / Fast diffusion sampling
Mobile-VTON: High-Fidelity On-Device Virtual Try-On
Zhenchen Wan, Ce Chen, Runqi Lin, Jiaxin Huang, Tianxi Chen, Yanwu Xu, Tongliang Liu, Mingming Gong
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 trajectory-consistent GarmentNet (TCG) (ablation) | Mobile-VTON · VITON-HD | LPIPS: 0.119 -> 0.111 | Improved |
| add TCG (ablation) | Mobile-VTON · VITON-HD | FID (unpaired, x100): 11.231 -> 10.814 | Improved |
| add latent concatenation (LC) on top of TCG (ablation) | Mobile-VTON · VITON-HD | LPIPS: 0.111 -> 0.088 | Improved |
| add LC on top of TCG (ablation) | Mobile-VTON · VITON-HD | FID (unpaired, x100): 10.814 -> 10.211 | Improved |
| add TCG and LC together (ablation) | Mobile-VTON · VITON-HD | CLIP-I: 0.798 -> 0.833 | Improved |
| use mobile-side mask-free Mobile-VTON instead of server-side IDM-VTON | virtual try-on · VITON-HD | LPIPS: 0.102 -> 0.088 | Improved |
| use Mobile-VTON instead of IDM-VTON | virtual try-on · VITON-HD | FID (unpaired, x100): 9.156 -> 10.211 | Hurt |
| use Mobile-VTON instead of IDM-VTON | virtual try-on · VITON-HD In-the-Wild | CLIP-I: 0.931 -> 0.902 | Hurt |
| use Mobile-VTON instead of BooW-VTON | virtual try-on · DressCode upper-body | SSIM: 0.928 -> 0.935 | Improved |
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.
- BooW-VTON — BooW-VTON: Boosting In-the-Wild Virtual Try-On via Mask-Free Pseudo Data Training (CVPR 2025) · better on 5 of 9 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 0.88)
- VTON 360: High-Fidelity Virtual Try-On from Any Viewing Direction (CVPR 2025 · similarity 0.87)
- M&M VTO: Multi-Garment Virtual Try-On and Editing (CVPR 2024 · similarity 0.87)
- OOTDiffusion: Outfitting Fusion Based Latent Diffusion for Controllable Virtual Try-On (AAAI 2025 · similarity 0.86)
- MV-VTON: Multi-View Virtual Try-On with Diffusion Models (AAAI 2025 · similarity 0.86)
- Correpondence Alignment For Improved Virtual Try-On (NeurIPS 2026 · similarity 0.85)
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.
