AI Paper Atlas

Research map / Image generation / Image restoration

Deep Semantic Face Deblurring

Ziyi Shen, Wei-Sheng Lai, Tingfa Xu, Jan Kautz, Ming-Hsuan Yang

CVPR 2018 · Image generation › Image restoration · approach: Image deblurring · 218 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 global semantic priors to content-loss training (ablation)Face deblurring CNN · Helen and CelebA test setsPSNR: 24.85 -> 25.32; 24.23 -> 24.32Improved
add global semantic priors to content-loss training (ablation)Face deblurring CNN · CelebA test setSSIM: 0.864 -> 0.864No clear effect
add local structural loss to global semantic priors (ablation)Face deblurring CNN · Helen and CelebA test setsPSNR: 25.32 -> 25.48; 24.32 -> 24.58Improved
add incremental training (ablation)Face deblurring CNN · Helen and CelebA test setsPSNR: 25.48 -> 25.55; 24.58 -> 24.61Improved
replace direct training with incremental training (ablation)Face deblurring CNN · Helen test set, different blur-kernel sizesPSNRImproved
add perceptual loss (ablation)Face deblurring CNN with incremental training · Helen and CelebA test setsPSNR: 25.55 -> 25.99; 24.61 -> 25.05Improved
add adversarial loss after perceptual loss (ablation)Face deblurring CNN · Helen and CelebA test setsPSNR: 25.99 -> 25.58; 25.05 -> 24.34Hurt
add adversarial loss after perceptual loss (ablation)Face deblurring CNN · Helen and CelebA test setsphotorealismImproved
use semantic priors and local structural lossesFace deblurring CNN · CelebA test settop-1 recognition accuracy: 42\% -> 54\%Improved
use semantic priors and local structural lossesFace deblurring CNN · CelebA test setface detection success rate: 95\% -> 99\%Improved
use the proposed face deblurring method instead of Nah et al.Face deblurring · Helen and CelebA test setsPSNR: 24.12 -> 25.58; 22.43 -> 24.34Improved
use the proposed face deblurring method instead of Nah et al.Face deblurring · 128 × 128 imagesexecution time (seconds): 0.09 -> 0.05Improved

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