Dual-Attention-Based Feature Aggregation Network for Infrared and Visible Image Fusion

Infrared and visible image fusion aims to produce fused images which retain rich texture details and high pixel intensity in the source images. In this paper, we propose a dual-attention based feature aggregation network for infrared and visible image fusion. Specifically, we first design a multi-branch channel attention based feature aggregation block by generating multiple branches to suppress useless features from different aspects. This block is also able to adaptively aggregate the meaningful features by exploiting the interdependencies between channel features. To gather more meaningful features during the fusion process, we further design a global-local spatial attention based feature aggregation block, for progressively integrating features of source images. After that, we introduce multi-scale structural similarity as loss function to evaluate the structural differences between the fused image and source images from multiple scales. In addition, the proposed network involves strong generalization ability since our fusion model is trained on the RoadScene dataset and tested directly on the TNO and MSRS datasets. Extensive experiments on these datasets demonstrate the superiority of our network compared to current state-of-the-art methods. The source code will be released at https://github.com/tangjunyang/Dual-attention.