Compressed Video Quality Enhancement: Classifying and Benchmarking over Standards
This work addresses the problem of inconsistent evaluation and model selection for researchers and practitioners in CVQE, though it is incremental as it synthesizes and organizes existing knowledge rather than proposing new methods.
This paper tackles the lack of systematic classification and benchmarking in compressed video quality enhancement (CVQE) research by introducing a novel taxonomy and a unified benchmarking framework, providing a comprehensive review to establish consistent assessment practices.
Compressed video quality enhancement (CVQE) is crucial for improving user experience with lossy video codecs like H.264/AVC, H.265/HEVC, and H.266/VVC. While deep learning based CVQE has driven significant progress, existing surveys still suffer from limitations: lack of systematic classification linking methods to specific standards and artifacts, insufficient comparative analysis of architectural paradigms across coding types, and underdeveloped benchmarking practices. To address these gaps, this paper presents three key contributions. First, it introduces a novel taxonomy classifying CVQE methods across architectural paradigms, coding standards, and compressed-domain feature utilization. Second, it proposes a unified benchmarking framework integrating modern compression protocols and standard test sequences for fair multi-criteria evaluation. Third, it provides a systematic analysis of the critical trade-offs between reconstruction performance and computational complexity observed in state-of-the-art methods and highlighting promising directions for future research. This comprehensive review aims to establish a foundation for consistent assessment and informed model selection in CVQE research and deployment.