A Retinex Decomposition Model-Based Deep Framework for Infrared and Visible Image Fusion

Infrared and visible image fusion (IVIF) aims to integrate complementary information between sensors and generate information-rich high-quality images. However, current methods mainly concentrate on the fusion of the source features from the sensors, ignoring the feature information mismatch caused by the property of the sensors, which results in redundant or even invalid information. To tackle the above challenges, this paper proposed an end-to-end model based on the Retinex Decomposition Model (RDM), which achieves hierarchical feature fusion by decoupling the illumination and reflectance components of source image, and alleviates the fusion performance degradation caused by feature-level mismatch, called RDMFuse. On the one hand, the contrast-texture module and the reflectance fusion function are designed for the property of the reflectance layer, which complements each other to aggregate the intrinsic information of the source images at a smaller cost and brings the fused image better visual effects. On the other hand, the illumination-adaptive module implements illumination layer optimization in a self-supervised way to make the fused image with an appropriate intensity distribution. It is worth noting that this mechanism implicitly improves the entropy quality of the image to improve the image degradation problem caused by environmental factors, especially in the case of a dark environment. Numerous experiments have demonstrated the effectiveness and robustness of the RDMFuse and the superiority of generalization in high-level vision tasks due to the improved discriminability of the fused image to the captured scene.