Breaking Free from Fusion Rule: A Fully Semantic-driven Infrared and Visible Image Fusion
This work addresses the challenge of improving fusion methods for computer vision applications, particularly for high-level tasks, though it appears incremental by building on existing semantic guidance approaches.
The paper tackles the problem of infrared and visible image fusion by developing a semantic-driven network that eliminates hand-crafted fusion rules, achieving superior performance in visual quality and high-level vision tasks compared to state-of-the-art methods.
Infrared and visible image fusion plays a vital role in the field of computer vision. Previous approaches make efforts to design various fusion rules in the loss functions. However, these experimental designed fusion rules make the methods more and more complex. Besides, most of them only focus on boosting the visual effects, thus showing unsatisfactory performance for the follow-up high-level vision tasks. To address these challenges, in this letter, we develop a semantic-level fusion network to sufficiently utilize the semantic guidance, emancipating the experimental designed fusion rules. In addition, to achieve a better semantic understanding of the feature fusion process, a fusion block based on the transformer is presented in a multi-scale manner. Moreover, we devise a regularization loss function, together with a training strategy, to fully use semantic guidance from the high-level vision tasks. Compared with state-of-the-art methods, our method does not depend on the hand-crafted fusion loss function. Still, it achieves superior performance on visual quality along with the follow-up high-level vision tasks.