Interactive Feature Embedding for Infrared and Visible Image Fusion
This work addresses the challenge of insufficient vital information extraction in image fusion for applications like surveillance or medical imaging, representing an incremental improvement over existing methods.
The paper tackles the problem of vital information degradation in unsupervised deep learning methods for infrared and visible image fusion by proposing a novel interactive feature embedding within a self-supervised learning framework, achieving favorable performance against state-of-the-art methods in qualitative and quantitative evaluations.
General deep learning-based methods for infrared and visible image fusion rely on the unsupervised mechanism for vital information retention by utilizing elaborately designed loss functions. However, the unsupervised mechanism depends on a well designed loss function, which cannot guarantee that all vital information of source images is sufficiently extracted. In this work, we propose a novel interactive feature embedding in self-supervised learning framework for infrared and visible image fusion, attempting to overcome the issue of vital information degradation. With the help of self-supervised learning framework, hierarchical representations of source images can be efficiently extracted. In particular, interactive feature embedding models are tactfully designed to build a bridge between the self-supervised learning and infrared and visible image fusion learning, achieving vital information retention. Qualitative and quantitative evaluations exhibit that the proposed method performs favorably against state-of-the-art methods.