AI Paper Atlas

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

CVPR 2026 · Image generation › Fast diffusion sampling · approach: Distillation for few-step generation · 0 citations (OpenAlex)

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 changedWhereMeasuredEffect
add trajectory-consistent GarmentNet (TCG) (ablation)Mobile-VTON · VITON-HDLPIPS: 0.119 -> 0.111Improved
add TCG (ablation)Mobile-VTON · VITON-HDFID (unpaired, x100): 11.231 -> 10.814Improved
add latent concatenation (LC) on top of TCG (ablation)Mobile-VTON · VITON-HDLPIPS: 0.111 -> 0.088Improved
add LC on top of TCG (ablation)Mobile-VTON · VITON-HDFID (unpaired, x100): 10.814 -> 10.211Improved
add TCG and LC together (ablation)Mobile-VTON · VITON-HDCLIP-I: 0.798 -> 0.833Improved
use mobile-side mask-free Mobile-VTON instead of server-side IDM-VTONvirtual try-on · VITON-HDLPIPS: 0.102 -> 0.088Improved
use Mobile-VTON instead of IDM-VTONvirtual try-on · VITON-HDFID (unpaired, x100): 9.156 -> 10.211Hurt
use Mobile-VTON instead of IDM-VTONvirtual try-on · VITON-HD In-the-WildCLIP-I: 0.931 -> 0.902Hurt
use Mobile-VTON instead of BooW-VTONvirtual try-on · DressCode upper-bodySSIM: 0.928 -> 0.935Improved

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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy