BSMamba：用于低光图像增强中长程交互的亮度与语义建模
BSMamba: Brightness and Semantic Modeling for Long-Range Interaction in Low-Light Image Enhancement
AI总结：
提出BSMamba视觉Mamba架构，通过亮度Mamba和语义Mamba分别优先连接亮度相似和语义相似的远距离token，解决低光图像增强中亮度提升与语义保持的难题，实现最先进性能。
摘要：
当前的低光图像增强（LLIE）方法在同时提升亮度、保持语义一致性、细节保真度和计算效率方面面临重大限制。随着状态空间模型（尤其是Mamba）的出现，图像恢复已取得显著性能，但现有的视觉Mamba方法使用固定扫描规则将二维图像展平为一维token序列，这严重限制了具有因果关系的远距离token之间的交互，并制约了其捕获有意义的长程依赖的能力。为解决这些根本性限制，我们提出了BSMamba，一种新颖的视觉Mamba架构，包含两个专门设计的组件：亮度Mamba和语义Mamba。亮度Mamba通过优先连接具有相似亮度水平的远距离token，革新了token交互模式，通过亮度引导的选择性注意力有效解决了LLIE任务中的亮度恢复挑战。作为补充，语义Mamba建立了具有相似语义含义的token之间的优先交互，使模型能够通过连接图像中语义相关的区域来保持上下文一致性，从而在增强过程中保留图像语义的层次性。通过基于亮度和语义相似性而非任意扫描模式智能地对token进行建模，BSMamba超越了传统token序列的约束，同时遵循因果建模的原则。大量实验表明，BSMamba在LLIE中实现了最先进的性能，同时保持了语义一致性。代码可在https://github.com/bywlzts/BSMamba获取。
英文摘要：
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. Code is available at https://github.com/bywlzts/BSMamba.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
