MaIR: A Locality- and Continuity-Preserving Mamba for Image Restoration

TL;DR

MaIR introduces a novel image restoration model that preserves local image features and effectively aggregates multiple sequences, achieving state-of-the-art results across various restoration tasks.

Contribution

The paper proposes NSS and SSA components that enhance Mamba-based restoration by maintaining locality and continuity and improving sequence aggregation.

Findings

MaIR surpasses 40 baselines on 14 datasets.

Achieves state-of-the-art performance in super-resolution, denoising, deblurring, and dehazing.

Code is publicly available for reproducibility.

Abstract

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.