BSMamba: Brightness and Semantic Modeling for Long-Range Interaction in Low-Light Image Enhancement

2025-06-23

AI Summary

Existing low-light image enhancement methods struggle to simultaneously achieve brightness enhancement, semantic consistency, and fine-detail preservation. Moreover, mainstream Vision Mamba models suffer from limited long-range token modeling due to fixed causal scanning orders. To address these issues, we propose a vision Mamba architecture with joint brightness and semantic modeling. Our method introduces a brightness-guided, semantic-aware selective attention mechanism that breaks causal scanning constraints to enable hierarchical long-range dependency modeling. Additionally, we design a dual-branch state-space model integrating brightness encoding and context-aware semantic aggregation. Evaluated on multiple benchmarks, our approach achieves state-of-the-art performance, significantly improving brightness restoration quality and semantic fidelity while preserving rich structural details and maintaining efficient inference.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Large Multimodal Models (LMMs)
• Search and Optimization: Learning to Search

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Large language models for search
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Current low-light image enhancement (LLIE) methods face significant limitations in simultaneously improving brightness while preserving semantic consistency, fine details, and computational efficiency. With the emergence of state-space models, particularly Mamba, image restoration has achieved remarkable performance, yet existing visual Mamba approaches flatten 2D images into 1D token sequences using fixed scanning rules, critically limiting interactions between distant tokens with causal relationships and constraining their ability to capture meaningful long-range dependencies. To address these fundamental limitations, we propose BSMamba, a novel visual Mamba architecture comprising two specially designed components: Brightness Mamba and Semantic Mamba. The Brightness Mamba revolutionizes token interaction patterns by prioritizing connections between distant tokens with similar brightness levels, effectively addressing the challenge of brightness restoration in LLIE tasks through brightness-guided selective attention. Complementing this, the Semantic Mamba establishes priority interactions between tokens sharing similar semantic meanings, allowing the model to maintain contextual consistency by connecting semantically related regions across the image, thus preserving the hierarchical nature of image semantics during enhancement. By intelligently modeling tokens based on brightness and semantic similarity rather than arbitrary scanning patterns, BSMamba transcends the constraints of conventional token sequencing while adhering to the principles of causal modeling. Extensive experiments demonstrate that BSMamba achieves state-of-the-art performance in LLIE while preserving semantic consistency.

Problem

• Improve brightness while preserving semantic consistency in low-light images
• Enhance long-range token interactions for better image restoration
• Maintain computational efficiency during low-light image enhancement

Innovation

• Brightness Mamba prioritizes distant token brightness connections
• Semantic Mamba links tokens by semantic similarity
• BSMamba combines brightness and semantic guided attention