AI Paper Atlas

Research map / Image generation / Image restoration

GT-Mean Loss: A Simple Yet Effective Solution for Brightness Mismatch in Low-Light Image Enhancement

Jingxi Liao, Shijie Hao, Richang Hong, Meng Wang

ICCV 2025 · Image generation › Image restoration · approach: Low-light image enhancement · 9 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
train with GT-mean loss instead of original lossUformer · LOLv1PSNR: 18.218 -> 18.915Improved
train with GT-mean loss instead of original lossCID-Net · LOLv1PSNR: 23.809 -> 25.122Improved
train with GT-mean loss instead of original lossUformer · LOLv2-realPSNR: 14.941 -> 16.103Improved
train with GT-mean loss instead of original lossLLFormer · LOLv2-syntheticPSNR: 24.195 -> 25.152Improved
train with GT-mean loss instead of original lossSNR-Aware · LOLv2-syntheticIAA: 2.209 -> 2.207Hurt
train with GT-mean loss instead of original lossCID-Net · LOLv1IQA: 4.087 -> 4.074Hurt
train with GT-mean loss instead of original lossRestormer · LOLv1LPIPS: 0.128 -> 0.122Improved
train with GT-mean loss instead of original lossMIRNet · LOLv2-realLPIPS: 0.313 -> 0.214Improved
train with GT-mean loss instead of original lossFive-model average on unpaired sets · DICM/MEF/LIME/NPE/VV (avg)NIQE: 6.880 -> 6.900Mixed
replace GT-mean loss with brightness-aligned loss only (ablation)RetinexFormer · LOLv1 trainingPSNR: 18.6 dB to 7.9 dBHurt
use hybrid schedule switching to brightness-aligned loss at 80K iterations instead of baseline L1 (ablation)RetinexFormer · LOLv1 trainingLPIPS: 0.155 -> 0.129Mixed
use dynamic weight W (GT-mean loss) instead of fixed phased hybrid (ablation)RetinexFormer · LOLv1 trainingLPIPS, PSNR, brightness discrepancyImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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