Exploring State Space Model in Wavelet Domain: An Infrared and Visible Image Fusion Network via Wavelet Transform and State Space Model

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhang, Tianpei, Zhu, Yiming, Zhao, Jufeng, Cui, Guangmang, Zheng, Yuchen
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915211466768384
author Zhang, Tianpei
Zhu, Yiming
Zhao, Jufeng
Cui, Guangmang
Zheng, Yuchen
author_facet Zhang, Tianpei
Zhu, Yiming
Zhao, Jufeng
Cui, Guangmang
Zheng, Yuchen
contents Deep learning techniques have revolutionized the infrared and visible image fusion (IVIF), showing remarkable efficacy on complex scenarios. However, current methods do not fully combine frequency domain features with global semantic information, which will result in suboptimal extraction of global features across modalities and insufficient preservation of local texture details. To address these issues, we propose Wavelet-Mamba (W-Mamba), which integrates wavelet transform with the state-space model (SSM). Specifically, we introduce Wavelet-SSM module, which incorporates wavelet-based frequency domain feature extraction and global information extraction through SSM, thereby effectively capturing both global and local features. Additionally, we propose a cross-modal feature attention modulation, which facilitates efficient interaction and fusion between different modalities. The experimental results indicate that our method achieves both visually compelling results and superior performance compared to current state-of-the-art methods. Our code is available at https://github.com/Lmmh058/W-Mamba.
format Preprint
id arxiv_https___arxiv_org_abs_2503_18378
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Exploring State Space Model in Wavelet Domain: An Infrared and Visible Image Fusion Network via Wavelet Transform and State Space Model
Zhang, Tianpei
Zhu, Yiming
Zhao, Jufeng
Cui, Guangmang
Zheng, Yuchen
Computer Vision and Pattern Recognition
Deep learning techniques have revolutionized the infrared and visible image fusion (IVIF), showing remarkable efficacy on complex scenarios. However, current methods do not fully combine frequency domain features with global semantic information, which will result in suboptimal extraction of global features across modalities and insufficient preservation of local texture details. To address these issues, we propose Wavelet-Mamba (W-Mamba), which integrates wavelet transform with the state-space model (SSM). Specifically, we introduce Wavelet-SSM module, which incorporates wavelet-based frequency domain feature extraction and global information extraction through SSM, thereby effectively capturing both global and local features. Additionally, we propose a cross-modal feature attention modulation, which facilitates efficient interaction and fusion between different modalities. The experimental results indicate that our method achieves both visually compelling results and superior performance compared to current state-of-the-art methods. Our code is available at https://github.com/Lmmh058/W-Mamba.
title Exploring State Space Model in Wavelet Domain: An Infrared and Visible Image Fusion Network via Wavelet Transform and State Space Model
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.18378