AI Paper Atlas

Research map / Image generation / Image restoration

Learning Data Terms for Non-blind Deblurring

Jiangxin Dong, Jinshan Pan, Deqing Sun, Zhixun Su, Ming-Hsuan Yang

ECCV 2018 · Image generation › Image restoration · approach: Image deblurring · 43 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
learn the data term shrinkage function instead of fixed l2 norm (ablation)TV-prior deblurring, impulse noise example · Impulse noise example image (Nf=0)PSNR: 19.26 -> 29.99Improved
learn the data term shrinkage function instead of fixed l1 norm (ablation)TV-prior deblurring, impulse noise example · Impulse noise example image (Nf=0)PSNR: 27.36 -> 29.99Improved
use stage-dependent instead of stage-independent data term parameters (ablation)Ours · Impulse noise example imagevisual qualityImproved
combine the learned data term with the EPLL priorEPLL · Images with outliersvisual qualityImproved
learned data term versus hand-crafted Cho model on impulse noise (1%)Cho · Impulse noise 1%PSNR: 27.73 -> 29.75Improved
learned data term versus EPLL on low Gaussian noise (1%)EPLL · Gaussian noise 1%PSNR: 27.64 -> 26.47Hurt
learned data term versus EPLL at high Gaussian noise (5%)EPLL · Gaussian noise 5%PSNR: 23.56 -> 23.73Improved
learned data term versus Cho on mixed noise 1%Cho · Mixed noise 1%PSNR: 27.15 -> 26.23Hurt
learned data term versus Cho on saturated pixelsCho · Saturated pixelsPSNR: 28.17 -> 29.55Improved

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