Fast and Physically Enriched Deep Network for Joint Low-Light Enhancement and Image Deblurring

Abstract

Joint low-light enhancement and deblurring is a challenging imaging inverse problem that estimates clean images from photography corrupted by both low-light and blurring artifacts. To address this task, we propose FELI, a Fast and physically Enriched deep neural network for joint Low-light enhancement and Image deblurring. In a departure from recently proposed end-to-end networks, FELI employs a learnable Decomposer during training based on Retinex theory that helps with low-light scene recovery. FELI’s encoded features are further enriched by an input reconstruction task cognizant of the blur model leading to effective deblurring. We introduce a new customized contrastive regularization (CCR) term that pulls the restored clean image closer to the ground truth while pushing it far away from both the input and reconstructed input. Experiments performed on challenging synthetic and real-world datasets demonstrate that FELI outperforms state-of-the-art methods at a lower computational cost.