CDFFusion: A Color-Deviation-Free Fusion Network for Nighttime Infrared and Visible Images

The purpose of infrared and visible image fusion is to integrate their complementary information into a single image, thereby increasing the amount of information expression. However, previous methods often struggle to extract information hidden in darkness, and existing methods, which integrate brightness enhancement and image fusion, can cause overexposure, image blocking effects, and color deviation. Therefore, we propose a visible light and infrared image fusion method, CDFFusion, for low-light scenarios. Specifically, our method consists of two stages: First, an encoder is designed to extract deep features of visible light and infrared images respectively. Then, combined with RetiNex theory, a decomposition network is designed at the feature level to separate the illuminance component and reflectance component of the visible light image. Next, the proposed formula is used to process the Cb and Cr components of the original visible light image. The features of the reflectance component and infrared features are concatenated and input into the fusion network to obtain the Y component of the fused image. Finally, it is concatenated with the processed Cb' and Cr' components of the visible light image to get the final fused image. Experimental results show that the proposed method can effectively alleviate overexposure and image blocking effects, and there is no color deviation at all.