Adaptive Mamba Network Guided by Mixture of Experts for Infrared and Visible Image Fusion
IEEE Signal Processing Letters · 2026 · 33 · 2141-2145
DOI: 10.1109/lsp.2026.3695796 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Signal Processing Letters, 2026. Verfasst von Quanrui Wen und 5 weiteren Autor:innen. Die Arbeit nennt 38 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Foundation of Yunnan Key Laboratory of Unmanned Autonomous Systems, Guangdong Natural Science Fund for Distinguished Young Scholar.
Abstract (Originalsprache)
Current mainstream methods for multimodal image fusion rely on CNN and Transformers, which often suffer from severe information loss or high computational complexity. However, state-space models offer a promising alternative with their linear complexity and reduced historical information loss. This paper proposes a novel adaptive Mamba network, named MGMFuse, for infrared and visible image fusion, aiming to seamlessly integrate thermal targets with high-resolution texture details. Specifically, feature extraction is performed using a dual-branch architecture. We design the MoEGMamba module that uses the Mixture of Experts’prompt generation mechanism to dynamically guide Mamba for adaptive state space modeling. Furthermore, a specialized mechanism is proposed to execute modality-specific channel-wise rectification and cross-modal interaction to align deep semantic features. Experimental results on multiple datasets demonstrate that the proposed algorithm outperforms existing methods. Furthermore, it significantly enhances the performance of downstream visual tasks.
Förderung
- National Natural Science Foundation of China
- Foundation of Yunnan Key Laboratory of Unmanned Autonomous Systems
- Guangdong Natural Science Fund for Distinguished Young Scholar
- Guangdong Basic and Applied Basic Research Foundation
Zitieren
APA
Wen, Q., Zhu, H., Chen, R., Tang, J., Liu, Q., & Yuan, D. (2026). Adaptive Mamba Network Guided by Mixture of Experts for Infrared and Visible Image Fusion. IEEE Signal Processing Letters, 33, 2141-2145. https://doi.org/10.1109/lsp.2026.3695796
Vancouver
Wen Q, Zhu H, Chen R, Tang J, Liu Q, Yuan D. Adaptive Mamba Network Guided by Mixture of Experts for Infrared and Visible Image Fusion. IEEE Signal Processing Letters. 2026;33:2141-2145. doi:10.1109/lsp.2026.3695796
BibTeX
@article{Wen2026,
author = {Wen, Quanrui and Zhu, Huayi and Chen, Rui and Tang, Jianing and Liu, Qiao and Yuan, Di},
title = {Adaptive Mamba Network Guided by Mixture of Experts for Infrared and Visible Image Fusion},
journal = {IEEE Signal Processing Letters},
year = {2026},
volume = {33},
pages = {2141--2145},
doi = {10.1109/lsp.2026.3695796}
}
EUVIMED