Saved in:
Bibliographic Details
Main Authors: Zhang, Yuze, Li, Lingjie, Lin, Qiuzhen, Ming, Zhong, Yu, Fei, Leung, Victor C. M.
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.08293
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914251300405248
author Zhang, Yuze
Li, Lingjie
Lin, Qiuzhen
Ming, Zhong
Yu, Fei
Leung, Victor C. M.
author_facet Zhang, Yuze
Li, Lingjie
Lin, Qiuzhen
Ming, Zhong
Yu, Fei
Leung, Victor C. M.
contents The Mamba architecture has been widely applied to various low-level vision tasks due to its exceptional adaptability and strong performance. Although the Mamba architecture has been adopted for spectral reconstruction, it still faces the following two challenges: (1) Single spatial perception limits the ability to fully understand and analyze hyperspectral images; (2) Single-scale feature extraction struggles to capture the complex structures and fine details present in hyperspectral images. To address these issues, we propose a multi-scale, multi-perceptual Mamba architecture for the spectral reconstruction task, called M3SR. Specifically, we design a multi-perceptual fusion block to enhance the ability of the model to comprehensively understand and analyze the input features. By integrating the multi-perceptual fusion block into a U-Net structure, M3SR can effectively extract and fuse global, intermediate, and local features, thereby enabling accurate reconstruction of hyperspectral images at multiple scales. Extensive quantitative and qualitative experiments demonstrate that the proposed M3SR outperforms existing state-of-the-art methods while incurring a lower computational cost.
format Preprint
id arxiv_https___arxiv_org_abs_2601_08293
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle M3SR: Multi-Scale Multi-Perceptual Mamba for Efficient Spectral Reconstruction
Zhang, Yuze
Li, Lingjie
Lin, Qiuzhen
Ming, Zhong
Yu, Fei
Leung, Victor C. M.
Computer Vision and Pattern Recognition
The Mamba architecture has been widely applied to various low-level vision tasks due to its exceptional adaptability and strong performance. Although the Mamba architecture has been adopted for spectral reconstruction, it still faces the following two challenges: (1) Single spatial perception limits the ability to fully understand and analyze hyperspectral images; (2) Single-scale feature extraction struggles to capture the complex structures and fine details present in hyperspectral images. To address these issues, we propose a multi-scale, multi-perceptual Mamba architecture for the spectral reconstruction task, called M3SR. Specifically, we design a multi-perceptual fusion block to enhance the ability of the model to comprehensively understand and analyze the input features. By integrating the multi-perceptual fusion block into a U-Net structure, M3SR can effectively extract and fuse global, intermediate, and local features, thereby enabling accurate reconstruction of hyperspectral images at multiple scales. Extensive quantitative and qualitative experiments demonstrate that the proposed M3SR outperforms existing state-of-the-art methods while incurring a lower computational cost.
title M3SR: Multi-Scale Multi-Perceptual Mamba for Efficient Spectral Reconstruction
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.08293