AI Paper Atlas

Research map / Image generation / Image restoration

Unsupervised Night Image Enhancement: When Layer Decomposition Meets Light-Effects Suppression

Yeying Jin, Wenhan Yang, Robby T. Tan

ECCV 2022 · Image generation › Image restoration · approach: Low-light image enhancement · 190 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 light-effects suppression network after layer decomposition (ablation)Decomposition network · real night imagesqualitative visibilityImproved
add layer decomposition before the suppression network (ablation)Light-effects suppression network · real night imagesqualitative visibilityImproved
add light-effects layer G guidance to the suppression network (ablation)Light-effects suppression network · real night imagesqualitative light-effects suppressionImproved
add structure and HF-features consistency loss (ablation)Light-effects suppression network · real night imagesqualitative artefacts and detailsImproved
train suppression and boosting jointly rather than in sequence (ablation)Suppression then boosting · real night imagesqualitative visibilityImproved
boost dark regions before suppressing light effects without joint training (ablation)Sequential pipeline · real night imagesqualitative light-effects suppressionHurt
suppress light effects first then boost without joint training (ablation)Sequential pipeline · real night imagesqualitative artefactsHurt
use proposed unsupervised method over best baselineOurs vs Yan · GTA5PSNR: 26.99 -> 29.79Improved
use proposed method over best baselineOurs vs Zhang · Syn-light-effectsPSNR: 16.30 -> 16.95Improved
use proposed method over KinD++Ours vs KinD++ · LOL-testPSNR: 17.752 -> 21.521Improved
use proposed method over KinD++Ours vs KinD++ · LOL-testLPIPS: 0.198 -> 0.235Hurt
use proposed method over DRBNOurs vs DRBN · LOL-RealPSNR: 19.66 -> 25.51Improved

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