Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

M2Retinexformer: Multi-Modal Retinexformer for Low-Light Image Enhancement

About

Low-light image enhancement is challenging due to complex degradations, including amplified noise, artifacts, and color distortion. While Retinex-based deep learning methods have achieved promising results, they primarily rely on single-modality RGB information. We propose M2Retinexformer (Multi-Modal Retinexformer), a novel framework that extends Retinexformer by incorporating depth cues, luminance priors, and semantic features within a progressive refinement pipeline. Depth provides geometric context that is invariant to lighting variations, while luminance and semantic features offer explicit guidance on brightness distribution and scene understanding. Modalities are extracted at multiple scales and fused through cross-attention, with adaptive gating dynamically balancing illumination-guided self-attention and cross-attention based on the reliability of auxiliary cues. Evaluations on the LOL, SID, SMID, and SDSD benchmarks demonstrate overall improvements over Retinexformer and recent state-of-the-art methods. Code and pretrained weights are available at https://github.com/YoussefAboelwafa/M2Retinexformer

Youssef Aboelwafa, Hicham G. Elmongui, Marwan Torki• 2026

Related benchmarks

TaskDatasetResultRank
Low-light Image EnhancementLOL v1
PSNR24.89
195
Low-light Image EnhancementLOL real v2
PSNR23.85
152
Low-light Image EnhancementLOL syn v2
PSNR27.12
148
Low-light Image EnhancementSID
PSNR24.84
70
Low-light Image EnhancementSMID
PSNR28.76
55
Low-light Image EnhancementSDSD outdoor
PSNR27.39
49
Low-light Image EnhancementSDSD indoor
PSNR30.48
37
Showing 7 of 7 rows

Other info

GitHub

Follow for update