Degradation-Aware Hierarchical Termination for Blind Quality Enhancement of Compressed Video

TL;DR

This paper introduces a degradation-aware hierarchical termination method for blind compressed video quality enhancement, utilizing multiscale degradation representations and dynamic stage adjustment to improve performance and efficiency.

Contribution

It proposes a pretrained degradation representation learning module and a hierarchical termination mechanism, addressing limitations of existing blind QECV methods and adapting to different compression levels.

Findings

Achieved 110% PSNR improvement over state-of-the-art blind methods at QP=22.

Reduced inference time by 50% at QP=22 compared to QP=42.

Effectively captures multiscale degradation information for artifact removal.

Abstract

Existing studies on Quality Enhancement for Compressed Video (QECV) predominantly rely on known Quantization Parameters (QPs), employing distinct enhancement models per QP setting, termed non-blind methods. However, in real-world scenarios involving transcoding or transmission, QPs may be partially or entirely unknown, limiting the applicability of such approaches and motivating the development of blind QECV techniques. Current blind methods generate degradation vectors via classification models with cross-entropy loss, using them as channel attention to guide artifact removal. However, these vectors capture only global degradation information and lack spatial details, hindering adaptation to varying artifact patterns at different spatial positions. To address these limitations, we propose a pretrained Degradation Representation Learning (DRL) module that decouples and extracts high-dimensional, multiscale degradation representations from video content to guide the artifact removal. Additionally, both blind and non-blind methods typically employ uniform architectures across QPs, hence, overlooking the varying computational demands inherent to different compression levels. We thus introduce a hierarchical termination mechanism that dynamically adjusts the number of artifact reduction stages based on the compression level. Experimental results demonstrate that the proposed approach significantly enhances performance, achieving a PSNR improvement of 110% (from 0.31 dB to 0.65 dB) over a competing state-of-the-art blind method at QP = 22. Furthermore, the proposed hierarchical termination mechanism reduces the average inference time at QP = 22 by half compared to QP = 42.