AI Paper Atlas

Research map / Image generation / Image restoration

Learning to Deblur Images with Exemplars

Jinshan Pan, Wenqi Ren, Zhe Hu, Ming–Hsuan Yang

TPAMI 2018 · Image generation › Image restoration · approach: Image deblurring · 82 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
replace exemplar search with CNN edge prediction (prediction step)edge prediction · 480 frontal-face test imagesprediction run time (s): 4260 -> 0.95Improved
replace exemplar search with CNN edge prediction (total)deblurring pipeline · 480 frontal-face test imagestotal run time (s): 4287 -> 27.95Improved
use CNN-predicted edges instead of exemplar edgeskernel estimation · frontal face synthetic setcumulative error ratioMixed
add predicted salient edges to kernel estimation (ablation)kernel estimation · frontal face synthetic setcumulative error ratioImproved
add coarse-to-fine strategy (ablation)kernel estimation without predicted edges · frontal face synthetic setcumulative error ratioNo clear effect
use blurred-input edges instead of matched exemplar edges (ablation)kernel estimation · frontal face synthetic setcumulative error ratioNo clear effect
use 3x3 filters in all layers with same receptive field (ablation)CNN edge predictor · frontal face datasetavg PSNR: 35.33 -> 35.55No clear effect
vary first-layer filter size from 9x9 to 21x21 (ablation)CNN edge predictor · blur kernel sizes 9x9 to 27x27PSNRNo clear effect
increase exemplar set size from 40 to 200 centers (ablation)exemplar-based method · 40 blurred test imagescumulative error ratioNo clear effect
increase CNN training images from 200 to 1500 (ablation)CNN-based method · 40 blurred test imagescumulative error ratioNo clear effect
iteratively update exemplar edges (ablation)exemplar-based method · face deblurringkernel estimation qualityImproved
add 1% or other noise to blurred inputs (ablation)matching criterion · exemplar matchingmatching accuracyNo clear effect

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