AI Paper Atlas

Research map / Image generation / Image restoration

Normalized Blind Deconvolution

Meiguang Jin, Stefan Roth, Paolo Favaro

ECCV 2018 · Image generation › Image restoration · approach: Image deblurring · 49 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 exact L2 blur normalization instead of L1 normalization (ablation)PN on BSDS · small BSDS dataset (72 blurry images)mean SSD error ratio: 2.211 -> 2.011Improved
add exact L2 blur normalization instead of L1 normalization (ablation)PN on BSDS · small BSDS dataset (72 blurry images)failure cases: 3 -> 0Improved
use principled normalization instead of heuristic weight decay scaled by kernel norm (ablation)PN on BSDS · small BSDS dataset (72 blurry images)mean SSD error ratio: 2.591 -> 2.011Improved
use normalization instead of additive explicit L2 blur prior (ablation)PN on BSDS · small BSDS dataset (72 blurry images)mean SSD error ratio: 2.487 -> 2.011Improved
use p=2 norm instead of larger p in the normalized prior (ablation)PN and FW · 12 BSDS images, 6 blursSSD error ratio: p = 2 performs best among the different Lp normsImproved
use p=2 instead of p=1 in the normalized prior (FW method) (ablation)FW · 12 BSDS images, 6 blursSSD error ratio: p=1 gets stuck at the trivial solutionImproved
increase p beyond 2 (ablation)blur estimate · BSDS blur biasweight alpha of true kernel: alpha decreases and kernel moves toward uniformHurt
use PN instead of Pan et al. on full BSDSblind deblurring · full BSDS dataset (3000 blurry images)mean SSD error ratio: 2.956 -> 2.067Improved
use PN instead of Pan et al. on full BSDSblind deblurring · full BSDS dataset (3000 blurry images)failure cases: 325 -> 94Improved
use PN instead of Pan et al. on SUNblind deblurring · SUN dataset (640 blurry images)mean SSD error ratio: 1.914 -> 2.299Hurt
use PN instead of Perrone & Favaro on SUNblind deblurring · SUN dataset (640 blurry images)maximum error ratio: 8.517 -> 6.764Improved
use PN instead of Pan et al. under 5% noiseblind deblurring · Levin dataset (32 images)normalized L2 error: 5.368 -> 4.202Improved

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