A Lightweight Low-Light Image Enhancement Network via Channel Prior and Gamma Correction
This addresses image quality issues in low-light conditions for computer vision applications, but it is incremental as it builds on existing priors and theories.
The authors tackled low-light image enhancement by proposing CPGA-Net, a lightweight network that combines channel priors and gamma correction, achieving superior performance with only 0.025 million parameters and 0.030 seconds inference time, and an efficient version with 0.018 million parameters and 0.006 seconds.
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.