提升扫描模式分形维数，让Mamba更好增强暗光图像。
Larger Hausdorff Dimension in Scanning Pattern Facilitates Mamba-Based Methods in Low-Light Image Enhancement
- 用希尔伯特选择性扫描提升分形维数，更有效探索特征空间。
- 在多个公开数据集上显著提升图像质量，且推理更快、耗能更低。
- 适合关注低光图像增强与Mamba模型优化的研究者。
我们提出一种创新方法，通过新型希尔伯特选择性扫描机制，提升Mamba框架扫描模式的豪斯多夫维数。该机制更有效地探索特征空间，捕捉精细尺度细节并提升整体覆盖范围。结果显著缓解了信息不一致问题，同时强化空间局部性，更好地捕获细微局部交互，且不牺牲长程依赖建模能力。在多个公开基准上的大量实验表明，该方法显著提升了现有Mamba-based暗光图像增强方法的定量指标与定性视觉效果，同时降低计算资源消耗并缩短推理时间。我们认为这一优化策略不仅推动了暗光图像增强的前沿进展，也为其他基于Mamba的技术应用提供了新思路。
原文摘要 · Abstract (English)
We propose an innovative enhancement to the Mamba framework by increasing the Hausdorff dimension of its scanning pattern through a novel Hilbert Selective Scan mechanism. This mechanism explores the feature space more effectively, capturing intricate fine-scale details and improving overall coverage. As a result, it mitigates information inconsistencies while refining spatial locality to better capture subtle local interactions without sacrificing the model's ability to handle long-range dependencies. Extensive experiments on publicly available benchmarks demonstrate that our approach significantly improves both the quantitative metrics and qualitative visual fidelity of existing Mamba-based low-light image enhancement methods, all while reducing computational resource consumption and shortening inference time. We believe that this refined strategy not only advances the state-of-the-art in low-light image enhancement but also holds promise for broader applications in fields that leverage Mamba-based techniques.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。