AI Paper Atlas

Research map / Image generation / Image restoration

Multinex: Lightweight Low-light Image Enhancement via Multi-prior Retinex

Alexandru Brateanu, Tingting Mu, Codruta O. Ancuti, Cosmin Ancuti

CVPR 2026 · Image generation › Image restoration · approach: Low-light image enhancement · 1 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 luminance guidance stack and luminance term to raw RGB network (ablation)Multinex · LOLv1PSNR: 14.15 -> 20.57Improved
add reflectance term to luminance-only model (ablation)Multinex · LOLv1PSNR: 20.57 -> 23.19Improved
add luminance term to reflectance-only model (ablation)Multinex · LOLv1PSNR: 18.50 -> 23.19Improved
add CWA to model without CWA or MSEF (ablation)Multinex fusion module · LOLv1PSNR: 19.92 -> 21.34Improved
add MSEF to model without CWA or MSEF (ablation)Multinex fusion module · LOLv1PSNR: 19.92 -> 22.27Improved
add CWA to MSEF-only fusion module (ablation)Multinex fusion module · LOLv1PSNR: 22.27 -> 23.19Improved
use CWA instead of CBAM spatial attention (ablation)Multinex · LOLv1PSNR: 20.44 -> 23.19Improved
use CWA instead of MHSA with pooling (ablation)Multinex · LOLv1PSNR: 21.67 -> 23.19Improved
use CWA instead of MDTA (ablation)Multinex · LOLv1PSNR: 22.39 -> 23.19Improved
use Multinex instead of LYT-Net at similar sizelightweight LLIE · LOLv1PSNR: 22.38 -> 23.19Improved
use Multinex instead of CIDNetlightweight LLIE · LOLv1PSNR: 23.81 -> 23.19Hurt
use Multinex-Nano instead of RSFNetmicro LLIE · LOLv2-synPSNR: 17.18 -> 21.05Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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