GMSR:Gradient-Guided Mamba for Spectral Reconstruction from RGB Images

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Xinying, Huang, Zhixiong, Zhang, Sifan, Zhu, Jiawen, Gamba, Paolo, Feng, Lin
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912063619596288
author Wang, Xinying
Huang, Zhixiong
Zhang, Sifan
Zhu, Jiawen
Gamba, Paolo
Feng, Lin
author_facet Wang, Xinying
Huang, Zhixiong
Zhang, Sifan
Zhu, Jiawen
Gamba, Paolo
Feng, Lin
contents Mainstream approaches to spectral reconstruction (SR) primarily focus on designing Convolution- and Transformer-based architectures. However, CNN methods often face challenges in handling long-range dependencies, whereas Transformers are constrained by computational efficiency limitations. Recent breakthroughs in state-space model (e.g., Mamba) has attracted significant attention due to its near-linear computational efficiency and superior performance, prompting our investigation into its potential for SR problem. To this end, we propose the Gradient-guided Mamba for Spectral Reconstruction from RGB Images, dubbed GMSR-Net. GMSR-Net is a lightweight model characterized by a global receptive field and linear computational complexity. Its core comprises multiple stacked Gradient Mamba (GM) blocks, each featuring a tri-branch structure. In addition to benefiting from efficient global feature representation by Mamba block, we further innovatively introduce spatial gradient attention and spectral gradient attention to guide the reconstruction of spatial and spectral cues. GMSR-Net demonstrates a significant accuracy-efficiency trade-off, achieving state-of-the-art performance while markedly reducing the number of parameters and computational burdens. Compared to existing approaches, GMSR-Net slashes parameters and FLOPS by substantial margins of 10 times and 20 times, respectively. Code is available at https://github.com/wxy11-27/GMSR.
format Preprint
id arxiv_https___arxiv_org_abs_2405_07777
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle GMSR:Gradient-Guided Mamba for Spectral Reconstruction from RGB Images
Wang, Xinying
Huang, Zhixiong
Zhang, Sifan
Zhu, Jiawen
Gamba, Paolo
Feng, Lin
Computer Vision and Pattern Recognition
Image and Video Processing
Mainstream approaches to spectral reconstruction (SR) primarily focus on designing Convolution- and Transformer-based architectures. However, CNN methods often face challenges in handling long-range dependencies, whereas Transformers are constrained by computational efficiency limitations. Recent breakthroughs in state-space model (e.g., Mamba) has attracted significant attention due to its near-linear computational efficiency and superior performance, prompting our investigation into its potential for SR problem. To this end, we propose the Gradient-guided Mamba for Spectral Reconstruction from RGB Images, dubbed GMSR-Net. GMSR-Net is a lightweight model characterized by a global receptive field and linear computational complexity. Its core comprises multiple stacked Gradient Mamba (GM) blocks, each featuring a tri-branch structure. In addition to benefiting from efficient global feature representation by Mamba block, we further innovatively introduce spatial gradient attention and spectral gradient attention to guide the reconstruction of spatial and spectral cues. GMSR-Net demonstrates a significant accuracy-efficiency trade-off, achieving state-of-the-art performance while markedly reducing the number of parameters and computational burdens. Compared to existing approaches, GMSR-Net slashes parameters and FLOPS by substantial margins of 10 times and 20 times, respectively. Code is available at https://github.com/wxy11-27/GMSR.
title GMSR:Gradient-Guided Mamba for Spectral Reconstruction from RGB Images
topic Computer Vision and Pattern Recognition
Image and Video Processing
url https://arxiv.org/abs/2405.07777