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

Hugging Face Daily Papers Papers
low-light-image-enhancement retinexformer multi-modal deep-learning image-enhancement

Summary

M2Retinexformer extends the Retinexformer framework for low-light image enhancement by incorporating depth, luminance, and semantic cues via cross-attention and adaptive gating, achieving state-of-the-art results on multiple benchmarks.

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
Original Article
View Cached Full Text

Cached at: 05/14/26, 12:18 PM

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

Source: https://huggingface.co/papers/2605.12556

https://huggingface.co/papers/2605.12556#m2retinexformer-multi-modal-retinexformer-for-low-light-image-enhancementM2Retinexformer: Multi-Modal Retinexformer for Low-Light Image Enhancement

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 proposeM2Retinexformer(Multi-Modal Retinexformer), a novel framework that extends Retinexformer by incorporatingdepth cues,luminance priors, andsemantic featureswithin 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 throughcross-attention, withadaptive gatingdynamically 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.

Similar Articles

M^{2}SNet: Multi-scale in Multi-scale Subtraction Network for Medical Image Segmentation

Papers with Code Trending

This paper proposes M2SNet, a multi-scale multi-scale subtraction network for medical image segmentation that uses subtraction operations to capture difference features between encoder levels, improving localization and edge sharpness. It achieves state-of-the-art performance on eleven datasets across four medical imaging modalities.

MirrorPPR: Exemplar-Based Portrait Photo Retouching

Hugging Face Daily Papers

MirrorPPR introduces an exemplar-based portrait retouching framework using Diffusion Transformer with LoRA adaptation and self-augmented training data, achieving superior quality and identity preservation.