FusionMamba: dynamic feature enhancement for multimodal image fusion with Mamba
Visual Intelligence · 31.12.2024 · 2 (1)
DOI: 10.1007/s44267-024-00072-9 ↗Kurz gefasst
Fachartikel in der Zeitschrift Visual Intelligence, online erschienen am 31.12.2024. Verfasst von Xinyu Xie und 4 weiteren Autor:innen. Die Arbeit wurde bisher 274-mal zitiert (Crossref) und nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Basic and Applied Basic Research Foundation of Guangdong Province, Macao Polytechnic University Grant.
Abstract (Originalsprache)
Multimodal image fusion aims to integrate information from different imaging techniques to produce a comprehensive, detail-rich single image for downstream vision tasks. Existing methods based on local convolutional neural networks (CNNs) struggle to capture global features efficiently, while Transformer-based models are computationally expensive, although they excel at global modeling. Mamba addresses these limitations by leveraging selective structured state space models (S4) to effectively handle long-range dependencies while maintaining linear complexity. In this paper, we propose FusionMamba, a novel dynamic feature enhancement framework that aims to overcome the challenges faced by CNNs and Vision Transformers (ViTs) in computer vision tasks. The framework improves the visual state-space model Mamba by integrating dynamic convolution and channel attention mechanisms, which not only retains its powerful global feature modeling capability, but also greatly reduces redundancy and enhances the expressiveness of local features. In addition, we have developed a new module called the dynamic feature fusion module (DFFM). It combines the dynamic feature enhancement module (DFEM) for texture enhancement and disparity perception with the cross-modal fusion Mamba module (CMFM), which focuses on enhancing the inter-modal correlation while suppressing redundant information. Experiments show that FusionMamba achieves state-of-the-art performance in a variety of multimodal image fusion tasks as well as downstream experiments, demonstrating its broad applicability and superiority.
Förderung
- National Natural Science Foundation of China
- Basic and Applied Basic Research Foundation of Guangdong Province
- Macao Polytechnic University Grant
Zitieren
APA
Xie, X., Cui, Y., Tan, T., Zheng, X., & Yu, Z. (2024). FusionMamba: dynamic feature enhancement for multimodal image fusion with Mamba. Visual Intelligence, 2(1). https://doi.org/10.1007/s44267-024-00072-9
Vancouver
Xie X, Cui Y, Tan T, Zheng X, Yu Z. FusionMamba: dynamic feature enhancement for multimodal image fusion with Mamba. Visual Intelligence. 2024;2(1). doi:10.1007/s44267-024-00072-9
BibTeX
@article{Xie2024,
author = {Xie, Xinyu and Cui, Yawen and Tan, Tao and Zheng, Xubin and Yu, Zitong},
title = {FusionMamba: dynamic feature enhancement for multimodal image fusion with Mamba},
journal = {Visual Intelligence},
year = {2024},
volume = {2},
number = {1},
doi = {10.1007/s44267-024-00072-9}
}
EUVIMED