Unsupervised Image Fusion Method based on Feature Mutual Mapping
This work addresses image fusion problems for applications like surveillance and medical imaging, but it is incremental as it builds on existing deep learning approaches.
The paper tackled the limitations of manually designed fusion functions and input-independent learning in deep learning-based image fusion by proposing an unsupervised adaptive method with a feature mutual mapping fusion module and dual-branch multi-scale autoencoder, achieving superior performance in visual perception and objective evaluation across infrared, visible, multi-focus, and medical image fusion tasks.
Deep learning-based image fusion approaches have obtained wide attention in recent years, achieving promising performance in terms of visual perception. However, the fusion module in the current deep learning-based methods suffers from two limitations, \textit{i.e.}, manually designed fusion function, and input-independent network learning. In this paper, we propose an unsupervised adaptive image fusion method to address the above issues. We propose a feature mutual mapping fusion module and dual-branch multi-scale autoencoder. More specifically, we construct a global map to measure the connections of pixels between the input source images. % The found mapping relationship guides the image fusion. Besides, we design a dual-branch multi-scale network through sampling transformation to extract discriminative image features. We further enrich feature representations of different scales through feature aggregation in the decoding process. Finally, we propose a modified loss function to train the network with efficient convergence property. Through sufficient training on infrared and visible image data sets, our method also shows excellent generalized performance in multi-focus and medical image fusion. Our method achieves superior performance in both visual perception and objective evaluation. Experiments prove that the performance of our proposed method on a variety of image fusion tasks surpasses other state-of-the-art methods, proving the effectiveness and versatility of our approach.