AI Paper Atlas

Research map / Image generation / Image restoration

End-to-end Interpretable Learning of Non-blind Image Deblurring

Thomas Eboli, Jian Sun, Jean Ponce

ECCV 2020 · Image generation › Image restoration · approach: Image deblurring · 55 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
solve least squares with CPCR instead of conjugate gradient (ablation)HQS TV-l1 · 160 synthetic imagesaverage PSNR (dB): 26.12 -> 26.27Improved
use CPCR instead of FFT with FDN padding (ablation)HQS TV-l1 · 160 synthetic imagesaverage PSNR (dB): 25.96 -> 26.27Improved
use edge padding for FFT deconvolution (ablation)HQS-FFT · 160 synthetic imagesaverage PSNR (dB): 20.69 -> 25.53Improved
increase inverse filter size ratio w_c0/w_k up to 2.2 (ablation)CPCR preconditioner · 160 images, lambda=0PSNRImproved
learn the CNN prox and preconditioner modules (LCHQS_F vs CHQS)CHQS · LevinPSNR (dB): 32.12 -> 35.15Improved
learn the CNN prox and preconditioner modules (LCHQS_F vs CHQS)CHQS · SunPSNR (dB): 30.36 -> 32.93Improved
add final-output-only fine-tuning stage (LCHQS_F vs LCHQS_G)LCHQS_G · Levin / SunPSNR (dB): 35.11 -> 35.15; 32.83 -> 32.93Improved
add final-output-only fine-tuning stage (ablation)LCHQS blind · uniform deblurring 5% noisePSNR (dB): 24.05 -> 24.21Improved
add final-output-only fine-tuning stage (ablation)LCHQS non-blind · uniform deblurring 5% noisePSNR (dB): 23.87 -> 23.95No clear effect
train a single blind model over noise levels instead of noise-specific models (ablation)LCHQS_G · uniform deblurring 1% / 5% noisePSNR (dB): 29.54 -> 29.22; 23.87 -> 24.05Mixed
use 2/3 CPCR iterations instead of 1 (ablation)LCHQS_G · Levin and SunPSNR (dB): +0.4/0.5dB over FDNImproved
use LCHQS instead of CG-based methodnon-uniform deblurring · 100 PASCAL images 1% noisePSNR (dB): 25.84 -> 26.98Improved

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