HPGN: Hybrid Priors-Guided Network for Compressed Low-Light Image Enhancement
This work addresses a practical issue for applications involving storage and transmission of low-light images, but it is incremental as it builds on existing methods by adding joint task capabilities.
The paper tackled the problem of enhancing compressed low-light images by proposing HPGN, a hybrid priors-guided network that integrates compression and illumination priors, achieving superior results in joint task enhancement.
In practical applications, low-light images are often compressed for efficient storage and transmission. Most existing methods disregard compression artifacts removal or hardly establish a unified framework for joint task enhancement of low-light images with varying compression qualities. To address this problem, we propose a hybrid priors-guided network (HPGN) that enhances compressed low-light images by integrating both compression and illumination priors. Our approach fully utilizes the JPEG quality factor (QF) and DCT quantization matrix to guide the design of efficient plug-and-play modules for joint tasks. Additionally, we employ a random QF generation strategy to guide model training, enabling a single model to enhance low-light images with different compression levels. Experimental results demonstrate the superiority of our proposed method..