AI Paper Atlas

Research map / Image generation / Image restoration

Learning Discriminative Data Fitting Functions for Blind Image Deblurring

Jinshan Pan, Jiangxin Dong, Yu-Wing Tai, Zhixun Su, Ming-Hsuan Yang

ICCV 2017 · 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
add learned data fitting weights instead of intensity only (ablation)blind deblurring kernel estimation · synthetic blurred imagesaverage PSNR (dB): 23.08 -> 31.88Improved
add learned data fitting weights instead of gradient only (ablation)blind deblurring kernel estimation · synthetic blurred imagesaverage PSNR (dB): 26.78 -> 31.88Improved
use learned weights instead of intensity for latent image and gradient for kernel (ablation)blind deblurring kernel estimation · synthetic blurred imagesaverage PSNR (dB): 30.52 -> 31.88Improved
learn intensity weight for kernel estimation (ablation)learned data fitting function · kernel estimationlearned weight of zero-order term: 0 -> 0No clear effect
use learned weights separately for non-blind deconvolutionlatent image restoration · non-blind deconvolutionlearned weight of intensity term: 0.2095Improved
learn weights instead of fixed intensity or gradient termsblind deblurring · Sun et al. benchmark (80 images)success rateImproved
use learned data fitting function in place of Xu et al. combinationblind deblurring run time · 255x255 imagerun time (s): 3.10 -> 4.93Hurt

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