AI Paper Atlas

Research map / Image generation / Editing and style transfer

High-Resolution Virtual Try-On with Misalignment and Occlusion-Handled Conditions

Sangyun Lee, Gyojung Gu, Sunghyun Park, Seunghwan Choi, Jaegul Choo

ECCV 2022 · Image generation › Editing and style transfer · approach: Virtual try-on · 191 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 condition aligning (ablation)HR-VITON · VITON-HD 1024x768 unpairedFID: 12.41 -> 10.91Improved
add condition aligning (KID) (ablation)HR-VITON · VITON-HD 1024x768 unpairedKID: 0.356 -> 0.179Improved
add feature fusion block (ablation)HR-VITON · VITON-HD 1024x768 unpairedFID: 12.41 -> 10.91Improved
add feature fusion block (KID) (ablation)HR-VITON · VITON-HD 1024x768 unpairedKID: 0.381 -> 0.179Improved
add both feature fusion block and condition aligning (ablation)HR-VITON · VITON-HD 1024x768 unpairedFID: 12.73 -> 10.91Improved
add both feature fusion block and condition aligning (KID) (ablation)HR-VITON · VITON-HD 1024x768 unpairedKID: 0.415 -> 0.179Improved
replace VITON-HD with unified condition generatorVITON-HD · VITON-HD 1024x768FID: 11.59 -> 10.91Improved
replace PF-AFN (parser-free) with segmentation-based HR-VITONPF-AFN · VITON-HD 1024x768FID: 14.01 -> 10.91Improved
replace ClothFlow-warping VITON-HD* with HR-VITONVITON-HD* (ClothFlow warping) · VITON-HD 1024x768FID: 11.55 -> 10.91Improved
replace ClothFlow-warping VITON-HD* with HR-VITONVITON-HD* (ClothFlow warping) · VITON-HD 1024x768KID: 0.2993 -> 0.1794Improved
increase warping freedom (appearance flow) without occlusion handlingVITON-HD* · VITON-HD 1024x768pixel-squeezing artifacts (qualitative)Hurt
add body part occlusion handling (ablation)HR-VITON · VITON-HD 1024x768pixel-squeezing artifacts (qualitative)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.

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