AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Linking Garment With Person via Semantically Associated Landmarks for Virtual Try-On

Keyu Yan, Tingwei Gao, Hui Zhang, Chengjun Xie

CVPR 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Margin-based face recognition losses · 21 citations (OpenAlex)

Read the paper

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 SAL-VTON instead of HR-VITONVirtual try-on · VITON-HD testPSNR: 21.90 -> 23.14Improved
use SAL-VTON instead of StyleFlowVirtual try-on · VITON testFID: 8.89 -> 5.74Improved
add deformable patches rather than fixed-size patches (ablation)SAL-VTON · VITON testPSNR: 28.03 -> 28.29Improved
add LASNL (ablation)SAL-VTON · VITON testPSNR: 27.66 -> 28.29Improved
add local flow and LASNL (ablation)SAL-VTON · VITON testPSNR: 25.81 -> 28.29Improved
add local flow and LASNL (ablation)SAL-VTON · VITON testFID: 6.99 -> 5.74Improved

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