MambaLIE: Scene Light Intensity-Boosted Low-Light Image Enhancement with State Space Model

2026-07-03

AI Summary

This work addresses the degradation of images captured by consumer-grade devices under low-light conditions, which stems from sensor limitations and adversely affects visual quality and downstream vision tasks. To tackle this challenge, the authors propose the Local Enhancement State Space Model (LESSM), which uniquely incorporates scene illumination intensity into state space modeling. LESSM features a dual-branch architecture that jointly optimizes global long-range dependencies and local detail enhancement while preserving linear computational complexity. Extensive experiments demonstrate that the proposed method consistently outperforms existing CNN- and Transformer-based approaches across four synthetic and five real-world datasets, achieving superior performance in enhancement accuracy, inference speed, and model compactness—making it particularly suitable for deployment on resource-constrained devices.

Abstract

Images captured by consumer electronic devices, such as mobile phones and digital cameras, often suffer from low-light degradation due to sensor limitations and imaging pipelines, which degrades visual quality and affects downstream vision tasks. Existing methods based on Convolutional Neural Networks (CNNs) and Transformers have dominated current low-light image enhancement (LIE) due to their excellent ability to model hierarchical features. However, CNNs operate in local receptive fields that cannot model long-range dependencies, while Transformers overcome this problem but incur substantial computational costs. To address these challenges, we propose MambaLIE, a Scene Light Intensity-Boosted Low-Light Image Enhancement method based on a State Space Model (SSM). We first introduce scene light intensity to improve the structural distribution of illumination, which is then gated with the low-light input to guide enhancement. To better model the illumination while maintaining computational efficiency, we propose the Locally Enhanced State Space Model (LESSM) for efficient light enhancement. Our LESSM contains two branches: an SSM branch and a Local Enhanced branch, where the former is used to model the long-range dependencies with linear time complexity, while the latter is used to enhance local feature representations. Extensive experiments demonstrate that MambaLIE outperforms state-of-the-art CNN-based and Transformer-based LIE methods on four widely used synthetic benchmarks and five publicly available real-world benchmarks in terms of accuracy, speed, and model size, making it suitable for practical deployment on resource-constrained devices.

Problem

• Low-Light Image Enhancement
• Scene Light Intensity
• Image Degradation
• Visual Quality
• Downstream Vision Tasks

Innovation

• State Space Model
• Low-Light Image Enhancement
• Scene Light Intensity
• Locally Enhanced SSM
• Computational Efficiency