LLEMamba: Low-Light Enhancement via Relighting-Guided Mamba with Deep Unfolding Network

TL;DR

LLEMamba is a low-light enhancement method combining deep unfolding with relighting-guided Mamba architecture, leveraging Retinex theory for interpretability and achieving superior results with lower computational complexity.

Contribution

It introduces a novel deep unfolding network with a relighting-guided Mamba architecture based on Retinex optimization, balancing interpretability and efficiency in low-light enhancement.

Findings

Outperforms state-of-the-art methods in quantitative metrics

Achieves lower distortion in visual results

Demonstrates reduced computational complexity

Abstract

Transformer-based low-light enhancement methods have yielded promising performance by effectively capturing long-range dependencies in a global context. However, their elevated computational demand limits the scalability of multiple iterations in deep unfolding networks, and hence they have difficulty in flexibly balancing interpretability and distortion. To address this issue, we propose a novel Low-Light Enhancement method via relighting-guided Mamba with a deep unfolding network (LLEMamba), whose theoretical interpretability and fidelity are guaranteed by Retinex optimization and Mamba deep priors, respectively. Specifically, our LLEMamba first constructs a Retinex model with deep priors, embedding the iterative optimization process based on the Alternating Direction Method of Multipliers (ADMM) within a deep unfolding network. Unlike Transformer, to assist the deep unfolding framework with multiple iterations, the proposed LLEMamba introduces a novel Mamba architecture with lower computational complexity, which not only achieves light-dependent global visual context for dark images during reflectance relight but also optimizes to obtain more stable closed-form solutions. Experiments on the benchmarks show that LLEMamba achieves superior quantitative evaluations and lower distortion visual results compared to existing state-of-the-art methods.