AI Paper Atlas

Research map / Image generation / Image restoration

Noise Self-Regression: A New Learning Paradigm to Enhance Low-Light Images Without Task-Related Data

Zhao Zhang, Suiyi Zhao, Xiaojie Jin, Mingliang Xu, Yi Yang, Shuicheng Yan, Meng Wang

TPAMI 2024 · Image generation › Image restoration · approach: Self-supervised image denoising · 35 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
shift noise mean (MS-NoiSER) instead of zero-mean (ablation)NoiSER · Average PSNR (LOL, LSRW)PSNR: 16.100 -> 16.328Improved
shift noise mean (MS-NoiSER) (ablation)NoiSER · LSRW (Huawei)PSNR: 15.726 -> 16.674Improved
shift noise mean (MS-NoiSER) (ablation)NoiSER · LOLPSNR: 17.574 -> 17.194Hurt
shift noise mean (MS-NoiSER) (ablation)NoiSER · LSRW (Nikon)PSNR: 15.553 -> 15.158Hurt
use early stopping instead of full convergence (ablation)NoiSER · LOLPSNR: 17.5748 -> 17.0250Hurt
raise noise variance to 3 (Var3) (ablation)NoiSER-ES · LOLNIQE: 3.7206 -> 3.6806Improved
raise noise variance to 3 (Var3) (ablation)NoiSER-ES · LOLPSNR: 17.0250 -> 14.9257Hurt
add instance normalization layer (ablation)NoiSER · LOL visualvisual qualityImproved
add TV regularization (ablation)NoiSER-Var3 · LOL visualvisual noiseImproved
use 3x3 instead of 1x1 convolution (ablation)NoiSER · LOL visualvisual qualityImproved
increase noise standard deviation (ablation)NoiSER · LOL visualbrightnessMixed
use full NoiSER instead of instance normalization alone (ablation)IN only · LOL visualvisual qualityImproved

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