Detachable image decomposition and illumination mapping search for low-light image enhancement

Fan Jia, Shen Mao, Zijian Huang, Tieyong Zeng

Abstract: Highlights•We propose a novel four-stage detachable framework for low-light image enhancement.•A novel network and a novel loss function are designed for image decomposition.•A searching scheme is proposed to find a mapping pattern between illumination maps.•We show that our method outperforms a batch of SOTA methods on several datasets.