AI Paper Atlas

Research map / Image generation / Editing and style transfer

MOFA-VTON: More Fashion Possibilities with Fine-Grained Adaptations in Virtual Try-On

Xiaoyu Han, Chenyang Wang, Jing Wang, Shunyuan Zheng, Quanling Meng, Shengping Zhang

CVPR 2026 · Image generation › Editing and style transfer · approach: Virtual try-on · 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 dual-region mask, region encoder and layout adjustment blocks (vs clothing-agnostic mask) (ablation)MOFA-VTON · VITON-HDFID unpaired: 11.10 -> 8.61Improved
add dual-region mask, region encoder and layout adjustment blocks (vs clothing-agnostic mask) (ablation)MOFA-VTON · VITON-HDFID paired: 7.79 -> 5.97Improved
add dual-region mask, region encoder and layout adjustment blocks (vs clothing-agnostic mask) (ablation)MOFA-VTON · VITON-HDLPIPS paired: 0.0826 -> 0.0632Improved
add layout adjustment blocks (ablation)MOFA-VTON · VITON-HDFID unpaired: 9.06 -> 8.61Improved
add layout adjustment blocks (ablation)MOFA-VTON · VITON-HDSSIM paired: 0.8717 -> 0.8870Improved
add layout adjustment blocks (ablation)MOFA-VTON · VITON-HDKID unpaired: 1.80 -> 1.17Improved
add transposed convolution and mask filtering (ablation)MOFA-VTON · VITON-HDFID unpaired: 8.78 -> 8.61Improved
add transposed convolution and mask filtering (ablation)MOFA-VTON · VITON-HDSSIM paired: 0.8818 -> 0.8870Improved
add transposed convolution and mask filtering (ablation)MOFA-VTON · VITON-HDKID paired: 1.01 -> 0.92Improved
add CLIP text embedding to region encoder (ablation)MOFA-VTON · VITON-HDFID unpaired: 8.77 -> 8.61Improved
add CLIP text embedding to region encoder (ablation)MOFA-VTON · VITON-HDFID paired: 6.02 -> 5.97Improved
add CLIP text embedding to region encoder (ablation)MOFA-VTON · VITON-HDLPIPS paired: 0.0633 -> 0.0632No clear effect

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