LENFusion: A Joint Low-Light Enhancement and Fusion Network for Nighttime Infrared and Visible Image Fusion

Abstract

Contemporary image fusion methods face challenges in meeting the demands of dim nighttime environments, often accompanied by the concealment of image details in dark regions. In this paper, we introduce a novel approach, named LENFusion, which achieves a beneficial interaction between low-light enhancement and image fusion in the form of a feedback loop. LENFusion is primarily divided into three components: Luminance Adjustment Network (LAN), Re-enhancement and Fusion Network (RFN), and Luminance Feedback Network (LFN). The enhancement is performed in two stages. In the initial stage, LAN applies adaptive luminance adjustment to the original visible image. Subsequently, RFN achieves secondary enhancement and feature fusion with a clever combination of dual-attention mechanism, which motivates the fusion results to have high contrast and sharpness. Finally, LFN utilizes the luminance feedback loss to guide the luminance information of the fused images back to the LAN, effectively avoiding inappropriate enhancement of the images that do not meet the fusion requirements. In addition, we propose a reference-free color loss method for nighttime image fusion. Extensive comparison and generalization experiments have verified the superior fusion performance of LANFusion. Our code will be publicly available at: https://github.com/Liling-yang/LENFsuion.