AI Paper Atlas

Research map / Image generation / Editing and style transfer

Full-Range Virtual Try-On With Recurrent Tri-Level Transform

Han Yang, Xinrui Yu, Ziwei Liu

CVPR 2022 · Image generation › Editing and style transfer · approach: Virtual try-on · 33 citations (OpenAlex)

Check 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
Use RT-VTON instead of DCTONVirtual try-on · VITON test set (overall)FID: 16.37 -> 11.66Improved
Use RT-VTON instead of ACGPNVirtual try-on · VITON test set (overall)FID: 16.46 -> 11.66Improved
Use RT-VTON instead of DCTONVirtual try-on · Non-standard clothes setFID: 20.42 -> 17.24Improved
Use RT-VTON instead of ACGPNVirtual try-on · Non-standard clothes setFID: 19.22 -> 17.24Improved
Add Tri-Level Transform instead of using a conventional Unet backbone (ablation)Semantic Generation Module · VITON semantic reconstructionMean IoU (%): 86.77 -> 88.11Improved
Add Tri-Level Transform instead of using a plain encoder-decoder (ablation)Semantic Generation Module · VITON semantic reconstructionMean IoU (%): 86.31 -> 88.11Improved

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