MaIR：一种保留局部性与连续性的Mamba图像复原模型
MaIR: A Locality- and Continuity-Preserving Mamba for Image Restoration
AI总结：
针对现有基于Mamba的图像复原方法忽略图像局部性、连续性及序列差异问题，提出含嵌套S形扫描策略与序列混洗注意力模块的MaIR模型，在14个数据集超40个基线上取得SOTA性能。
摘要：
Mamba的最新进展在图像复原任务中展现出可观效果。这类方法通常将二维图像沿行和列展平为多个独立的一维序列，使用选择性扫描操作独立处理每个序列，再重新组合得到输出。然而，该范式忽略了两个关键方面：一、自然图像固有的局部关系与空间连续性；二、通过完全不同方式展开的序列之间存在的差异。为克服这些缺陷，我们探究了基于Mamba的复原方法中的两个问题：一、如何设计一种既能保留局部性与连续性、又有助于复原的扫描策略；二、如何聚合以完全不同方式展开的各异序列。针对上述问题，我们提出了一种新型基于Mamba的图像复原模型（MaIR），该模型由嵌套S形扫描策略（NSS）和序列混洗注意力模块（SSA）构成。具体而言，NSS分别通过基于条带的扫描区域和S形扫描路径，分别保留输入图像的局部性与连续性。SSA通过计算不同序列对应通道内的注意力权重实现序列聚合。得益于NSS和SSA，MaIR在14个具有挑战性的数据集上超越了40个基线模型，在图像超分辨率、去噪、去模糊和去雾任务上取得了最先进的性能。代码可在https://github.com/XLearning-SCU/2025-CVPR-MaIR获取。
英文摘要：
Recent advancements in Mamba have shown promising results in image restoration. These methods typically flatten 2D images into multiple distinct 1D sequences along rows and columns, process each sequence independently using selective scan operation, and recombine them to form the outputs. However, such a paradigm overlooks two vital aspects: i) the local relationships and spatial continuity inherent in natural images, and ii) the discrepancies among sequences unfolded through totally different ways. To overcome the drawbacks, we explore two problems in Mamba-based restoration methods: i) how to design a scanning strategy preserving both locality and continuity while facilitating restoration, and ii) how to aggregate the distinct sequences unfolded in totally different ways. To address these problems, we propose a novel Mamba-based Image Restoration model (MaIR), which consists of Nested S-shaped Scanning strategy (NSS) and Sequence Shuffle Attention block (SSA). Specifically, NSS preserves locality and continuity of the input images through the stripe-based scanning region and the S-shaped scanning path, respectively. SSA aggregates sequences through calculating attention weights within the corresponding channels of different sequences. Thanks to NSS and SSA, MaIR surpasses 40 baselines across 14 challenging datasets, achieving state-of-the-art performance on the tasks of image super-resolution, denoising, deblurring and dehazing. The code is available at https://github.com/XLearning-SCU/2025-CVPR-MaIR.
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。
