paper-with-me

Papers

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

2024-12-28 · CVPR 2025 1 · Boyun Li, Haiyu Zhao, Wenxin Wang, Peng Hu, Yuanbiao Gou, Xi Peng

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. Our codes will be available after acceptance.

📄 PDF Abstract BibTeX arXiv:2412.20066

Code (1)

XLearning-SCU/2025-CVPR-MaIR 공식 구현 pytorch

Tasks

DeblurringDenoisingImage DeblurringImage DehazingImage DenoisingImage RestorationImage Super-ResolutionMambaSingle Image DehazingSuper-Resolution

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음
Mamba Foundation models, now powering most of the exciting applications in deep learning, are almost universally based on the Transformer architecture and its core attention module.…

Similar Papers 제목 키워드 기반

WaMaIR: Image Restoration via Multiscale Wavelet Convolutions and Mamba-based Channel Modeling with Texture Enhancement

2025-10-19 · Shengyu Zhu, Congyi Fan, Fuxuan Zhang arxiv

Image restoration is a fundamental and challenging task in computer vision, where CNN-based frameworks demonstrate significant computational efficiency. However, previous CNN-based methods often face challenges in adequa…

Computational EfficiencyImage Restoration

Scaling Vision Mamba Across Resolutions via Fractal Traversal

2025-05-20 · Bo Li, Haoke Xiao, Lv Tang

Vision Mamba has recently emerged as a promising alternative to Transformer-based architectures, offering linear complexity in sequence length while maintaining strong modeling capacity. However, its adaptation to visual…

Change Detectionimage-classificationImage ClassificationMamba+3

PathMamba: A Hybrid Mamba-Transformer for Topologically Coherent Road Segmentation in Satellite Imagery

2025-11-26 · Jules Decaestecker, Nicolas Vigne arxiv

Achieving both high accuracy and topological continuity in road segmentation from satellite imagery is a critical goal for applications ranging from urban planning to disaster response. State-of-the-art methods often rel…

Road Segmentation

Progressive Split Mamba: Effective State Space Modelling for Image Restoration

2026-03-10 · Mohammed Hassanin, Nour Moustafa, Weijian Deng, Ibrahim Radwan arxiv

Image restoration requires simultaneously preserving fine-grained local structures and maintaining long-range spatial coherence. While convolutional networks struggle with limited receptive fields, and Transformers incur…

Image Restoration

EventMamba: Enhancing Spatio-Temporal Locality with State Space Models for Event-Based Video Reconstruction

2025-03-25 · Chengjie Ge, Xueyang Fu, Peng He, Kunyu Wang 외

Leveraging its robust linear global modeling capability, Mamba has notably excelled in computer vision. Despite its success, existing Mamba-based vision models have overlooked the nuances of event-driven tasks, especiall…

Event-Based Video ReconstructionMambaState Space ModelsVideo Reconstruction