AI Paper Atlas

Research map / Detection and segmentation / CNN features

FashionMirror: Co-Attention Feature-Remapping Virtual Try-On With Sequential Template Poses

Chieh-Yun Chen, Ling Lo, Pin-Jui Huang, Hong-Han Shuai, Wen-Huang Cheng

ICCV 2021 · Detection and segmentation › CNN features · approach: Local features and context in CNNs · 33 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 per-frame source human feature enhancement (hs boost) (ablation)FashionMirror · Fashion video try-on test set (2000 clips)LPIPS: 0.073 -> 0.057Improved
add per-frame source human feature enhancement (hs boost) (ablation)FashionMirror · Fashion video try-on test set (2000 clips)VFID (I3D): 4.593 -> 3.097Improved
add per-frame source human feature enhancement (hs boost) (ablation)FashionMirror · Fashion video try-on test set (2000 clips)SSIM: 0.906 -> 0.923Improved
add layer weighting lambda_ci in clothing feature fusion (ablation)FashionMirror · Fashion video try-on test set (2000 clips)LPIPS: 0.060 -> 0.057Improved
add layer weighting lambda_ci in clothing feature fusion (ablation)FashionMirror · Fashion video try-on test set (2000 clips)VFID (3D-ResNet): 1.206 -> 1.033Improved
add layer weighting lambda_ci in clothing feature fusion (ablation)FashionMirror · Fashion video try-on test set (2000 clips)IS: 2.187 -> 2.234Hurt
use single-flow STN instead of multi-flow feature enhancement (ablation)FashionMirror · Fashion video try-on test set (2000 clips)VFID (I3D): 5.226 -> 3.097Improved
use single-flow STN instead of multi-flow feature enhancement (ablation)FashionMirror · Fashion video try-on test set (2000 clips)LPIPS: 0.092 -> 0.057Improved
use co-attention mask network instead of semantic segmentationtry-on preprocessing · Runtime (40,000 input sets, 2080-ti)seconds per input: 0.3469 -> 0.1983Improved
fuse at feature level with FashionMirror instead of pixel-level pipelines (vs ACGPN + GFLA)FashionMirror · Fashion video try-on test set (2000 clips)VFID (I3D): 4.809 -> 3.097Improved
FashionMirror versus FashionOn on Inception ScoreFashionMirror · Fashion video try-on test set (2000 clips)IS: 2.388 -> 2.234Hurt

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