AI Paper Atlas

Research map / Image generation / Editing and style transfer

Toward Accurate and Realistic Outfits Visualization With Attention to Details

Kedan Li, Min Jin Chong, Jeffrey Zhang, Jingen Liu

CVPR 2021 · Image generation › Editing and style transfer · approach: Virtual try-on · 36 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 multiple coordinated garment warps rather than a single warp (ablation)OVNet · Multi-category dataset, overallFID∞: 1.577 -> .874Improved
increase the warp count from 4 to 8 (ablation)OVNet · Multi-category dataset, overallFID∞: .874 -> .872Improved
increase the warp count from 4 to 8 (ablation)OVNet · Multi-category dataset, topsFID∞: 1.163 -> 1.165Hurt
match garments to compatible model poses rather than sampling random pairsOVNet · Resampled test setFID∞: 9.81 -> 7.02Improved
match garments to compatible model poses rather than sampling random pairsCP-VTON · Resampled test setFID∞: 15.11 -> 13.42Improved
match garments to compatible model poses rather than sampling random pairsACGPN · Resampled test setFID∞: 11.13 -> 9.03Improved
use OVNet's multi-warp garment generation pipeline instead of the strongest listed baselineVITON test set · VITON test setSSIM: .845 -> .852Improved
use OVNet's multi-warp garment generation pipeline instead of the strongest listed baselineVITON test set · VITON test setIS: 2.829 -> 2.846Improved

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