AI Paper Atlas

Research map / Image generation / Editing and style transfer

Progressive Semantic-Aware Style Transformation for Blind Face Restoration

Chaofeng Chen, Xiaoming Li, Lingbo Yang, Xianhui Lin, Lei Zhang, Kwan-Yee K. Wong

CVPR 2021 · Image generation › Editing and style transfer · approach: Identity-preserving face manipulation · 174 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 PSFR-GAN instead of WaveletSRNetBlind face restoration · CelebAHQ-TestPSNR: 23.50 -> 23.64Improved
Use PSFR-GAN instead of WaveletSRNetBlind face restoration · CelebAHQ-TestSSIM: 0.6595 -> 0.6557Hurt
Use PSFR-GAN instead of DFDNetBlind face restoration · CelebAHQ-TestMSSIM: 0.7650 -> 0.7740Improved
Use PSFR-GAN instead of DFDNetBlind face restoration · CelebAHQ-TestLPIPS: 0.3791 -> 0.3042Improved
Use PSFR-GAN instead of DFDNetBlind face restoration · CelebAHQ-TestFID: 37.34 -> 23.20Improved
Use PSFR-GAN instead of DFDNetBlind face restoration · PSFR-RealTestFID: 37.63 -> 30.39Improved
Add parsing-map guidance (ablation)PSFR-GAN with LQ input only · PSFR-RealTestFID: 47.48 -> 32.37Improved
Add semantic-aware style loss (ablation)PSFR-GAN with LQ input only · PSFR-RealTestFID: 47.48 -> 34.22Improved
Add both parsing-map guidance and semantic-aware style loss (ablation)PSFR-GAN with LQ input only · PSFR-RealTestFID: 47.48 -> 30.39Improved
Remove parsing-map guidance (ablation)Full PSFR-GAN · PSFR-RealTestFID: 30.39 -> 34.22Hurt
Remove semantic-aware style loss (ablation)Full PSFR-GAN · PSFR-RealTestFID: 30.39 -> 32.37Hurt
Add high-resolution face pixel supervision to parsing-network training (ablation)LQ face parsing network · Natural low-resolution face parsingparsing qualityImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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