Low-light image enhancement with quality-oriented pseudo labels via semi-supervised contrastive learning

Nanfeng Jiang, Yiwen Cao, Xu-Yao Zhang, Da-Han Wang, Yifan He, Chiming Wang, Shunzhi Zhu

Abstract: Existing Low-Light Image Enhancement (LLIE) methods exhibit limitations when applied to complex scenes, primarily due to the lack of adaptation to real-world and synthetic images. To address this issue, we introduce a novel approach that leverages the mean-teacher strategy and contrastive regularization within a Contrastive Semi-Learning Network (CSL-Net). Specially, our CSL-Net employs high-quality pseudo labels to significantly improve model robustness and generalization. The novelties of this paper lie in: (1) We utilize a score-pool to store teacher’s and student’s outputs during training. After that, we propose a monotonic strategy to determine the most reliable Non-Reference Image Quality Assessment (NR-IQA) metric, which provides effective evaluations and determines the optimal output as the pseudo-label. (2) We integrate this selected pseudo-label with a contrastive loss to provide auxiliary information that mitigates overfitting issues and guides student towards generating realistic images. (3) In network design, we incorporate illumination and gradient priors to refine color appearance and detail preservation, facilitated by several elaborated modules, including Contextual Refinement Blocks (CRBs), Non-Local Dynamic Attention (NLDA) and Illumination Perceptual Enhancer (IPE). Experimental results on popular datasets demonstrate that the enhancement quality can be significantly improved by our proposed method.