AI Paper Atlas

Research map / Image generation / Editing and style transfer

All Parts Matter: A Unified Mask-Free Virtual Try-On Framework

Chenghu Du, Shengwu Xiong, Yi Rong

ICCV 2025 · Image generation › Editing and style transfer · approach: Virtual try-on · 2 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 text-driven pseudo-input preparation (ablation)Mask-free try-on baseline (PbE teacher-student) · VITONFID: 12.56 -> 9.86Improved
add text-driven pseudo-input preparation (ablation)Mask-free try-on baseline (PbE teacher-student) · VITONSSIM: 0.83 -> 0.87Improved
add texture-aware injection (ablation)Mask-free try-on baseline (PbE teacher-student) · VITONFID: 9.86 -> 9.61Improved
add texture-aware injection (ablation)Mask-free try-on baseline (PbE teacher-student) · VITONSSIM: 0.87 -> 0.89Improved
add refining conditional inference (ablation)Mask-free try-on baseline (PbE teacher-student) · VITONFID: 9.61 -> 9.52Improved
add refining conditional inference (ablation)Mask-free try-on baseline (PbE teacher-student) · VITONSSIM: 0.89 -> 0.91Improved
add gated manipulation (ablation)Mask-free try-on baseline (PbE teacher-student) · training convergenceepochs to converge: 75 epochs -> 10 epochsImproved
full method vs best prior on DressCode Upper FIDOurs · DressCode UpperFID: 9.54 -> 10.95Hurt
full method vs best prior on VITON-HD FIDOurs · VITON-HDFID: 9.410 -> 9.384Improved
full method vs best prior on VITON FIDOurs · VITONFID: 9.58 -> 9.52Improved
full method vs StableVITON on DressCode Upper KIDOurs · DressCode UpperKID: 0.72 -> 1.78Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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