Human vision relies heavily on available ambient light to perceive objects. Low-light scenes pose two distinct challenges: information loss due to insufficient illumination and undesirable brightness shifts. Low-light image enhancement (LLIE) refers to image enhancement technology tailored to handle this scenario. We introduce CPGA-Net, an innovative LLIE network that combines dark/bright channel priors and gamma correction via deep learning and integrates features inspired by the Atmospheric Scattering Model and the Retinex Theory. This approach combines the use of traditional and deep learning methodologies, designed within a simple yet efficient architectural framework that focuses on essential feature extraction. The resulting CPGA-Net is a lightweight network with only 0.025 million parameters and 0.030 seconds for inference time, yet it achieves superior performance over existing LLIE methods on both objective and subjective evaluation criteria. Furthermore, we utilized knowledge distillation with explainable factors and proposed an efficient version that achieves 0.018 million parameters and 0.006 seconds for inference time. The proposed approaches inject new solution ideas into LLIE, providing practical applications in challenging low-light scenarios.

翻译：人类视觉高度依赖环境光照来感知物体。低光场景带来两个显著挑战：光照不足导致的信息丢失以及不期望的亮度偏移。低光图像增强（LLIE）是指专门针对此类场景设计的图像增强技术。我们提出CPGA-Net，一种创新的LLIE网络，通过深度学习融合暗/亮通道先验与伽马校正，并整合受大气散射模型及Retinex理论启发的特征。该方法结合了传统与深度学习技术，设计于一个简洁高效的架构框架内，专注于核心特征提取。所得到的CPGA-Net是一个轻量级网络，仅含0.025百万个参数，推理时间为0.030秒，但在主客观评估标准上均优于现有LLIE方法。此外，我们利用可解释因子进行知识蒸馏，提出了一种高效版本，参数缩减至0.018百万个，推理时间降至0.006秒。本文提出的方法为LLIE注入了新的解决思路，为挑战性低光场景提供了实用应用。