AI Paper Atlas

Research map / Image generation / Editing and style transfer

Weakly Supervised High-Fidelity Clothing Model Generation

Ruili Feng, Cheng Ma, Chengji Shen, Xin Gao, Zhenjiang Liu, Xiaobo Li, Kairi Ou, Deli Zhao, Zheng-Jun Zha

CVPR 2022 · Image generation › Editing and style transfer · approach: Virtual try-on · 10 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 DGP instead of VITON-HDClothing model generation · CMI, 512×512FID: 87.5 -> 51.6Improved
Use DGP instead of VITON-HDClothing model generation · CMI, 512×512SWD: 56.1 -> 22.4Improved
Use DGP instead of VITON-HDClothing model generation · MPV, 512×512FID: 40.6 -> 48.4Hurt
Use DGP instead of VITON-HDClothing model generation · MPV, 512×512SWD: 52.7 -> 36.7Improved
Use DGP instead of PF-AFNClothing model generation · CMI, 128×128FID: 86.6 -> 56.5Improved
Use DGP instead of PF-AFNClothing model generation · CMI, 128×128SWD: 29.4 -> 18.8Improved
Use DGP instead of VITON-HDClothing model generation · MPV, 128×128FID: 44.7 -> 46.8Hurt
Use DGP instead of PF-AFNClothing model generation · MPV, 128×128SWD: 24.9 -> 29.9Hurt
Add semantic search after projection (ablation)DGP · CMIFID: 54.2 -> 52.9Improved
Add semantic search after projection (ablation)DGP · CMISWD: 56.7 -> 45.7Improved
Add pattern search (ablation)DGP · CMIFID: 52.9 -> 58.9Hurt
Add pattern search (ablation)DGP · CMISWD: 45.7 -> 46.5Hurt

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