融合压缩与光照先验，统一增强不同压缩质量的暗光图像
HPGN: Hybrid Priors-Guided Network for Compressed Low-Light Image Enhancement
- 结合JPEG质量因子和量化矩阵，设计可插拔模块
- 单模型实现多压缩等级暗光图像增强
- 适用于实际中压缩传输的暗光图像处理
在实际应用中，低光图像常被压缩以实现高效存储和传输。现有方法大多忽略压缩伪影去除，或难以建立统一框架来联合处理不同压缩质量的低光图像。为此，我们提出一种高效的混合先验引导网络（HPGN），通过融合压缩先验和光照先验来增强压缩低光图像。该方法充分利用JPEG质量因子（QF）和DCT量化矩阵（QM）指导高效即插即用模块的设计，并采用随机生成质量因子策略进行模型训练，使单一模型可适应不同压缩水平的低光图像。实验结果表明，所提方法具有明显优势。
原文摘要 · Abstract (English)
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 an efficient 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 (QM) 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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。