A Survey of Deep-Learning-Based Compressed Video Quality Enhancement

With the rapid growth of digital media applications, the need for advanced video compression technology has become indispensable, as achieving high compression ratios often leads to quality degradation, making compressed video quality enhancement a crucial research focus. In recent years, deep learning-based approaches have revolutionized compressed video quality enhancement, far surpassing traditional methods and enabling unprecedented high-quality reconstruction. Leveraging data-driven techniques, deep learning has demonstrated remarkable progress in image and video quality enhancement tasks. This study offers a comprehensive review of recent advances in the enhancement of compressed video quality. It focuses on deep learning-based methods, particularly those leveraging convolutional neural networks, and explores their advantages over traditional approaches. The review is structured around key topics, including task definitions and challenges, general-purpose and domain-specific quality enhancement techniques, as well as datasets and metrics. Beyond summarizing the state of the art, this article offers an in-depth analysis of current methods, highlighting their strengths, limitations, and practical application scenarios. Finally, it identifies future research directions and discusses the critical challenges that remain, with the aim of guiding further exploration in the field of compressed video quality enhancement.