AI Paper Atlas

Research map / Image generation / Image restoration

Blind Image Deblurring with Unknown Kernel Size and Substantial Noise

Zhong Zhuang, Taihui Li, Hengkang Wang, Ju Sun

IJCV 2023 · Image generation › Image restoration · approach: Image deblurring · 36 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
use l1/l2 instead of l1 regularizer on image gradient (ablation)double-DIP blind deblurring · Levin, low Gaussian noisePSNR (dB): 31.12 -> 32.64Improved
use l1/l2 instead of l1 regularizer on image gradient (ablation)double-DIP blind deblurring · Levin, high Gaussian noisePSNR (dB): 24.34 -> 27.74Improved
use l1/l2 so one lambda works across noise levels (ablation)double-DIP blind deblurring · Levin, Gaussian noiseoptimal lambda_x: 0.0001 -> 0.0002Improved
replace MLP-based DIP for the kernel with SIREN (ablation)double-DIP blind deblurring · synthetic noisy blurkernel and image qualityImproved
add windowed-moving-variance early stoppingdouble-DIP blind deblurring · high Gaussian noisePSNR curveImproved
increase regularization strength instead of early stopping (ablation)double-DIP blind deblurring · Gaussian noise sigma=0.05PSNR curveNo clear effect
overspecify kernel size up to half the image sizeproposed method vs other single-instance methods · LEVIN11 and LAI16PSNR, SSIM, VIF, LPIPSImproved
use Huber robust loss instead of MSEdouble-DIP blind deblurring · LAI16 impulse, shot noisePSNR, SSIM, VIF, LPIPSImproved

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