Saved in:
Bibliographic Details
Main Authors: Yu, Li, Zhao, Yingbo, Wu, Shiyu, Yu, Siyue, Gabbouj, Moncef, Liu, Qingshan
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.16137
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912720625860608
author Yu, Li
Zhao, Yingbo
Wu, Shiyu
Yu, Siyue
Gabbouj, Moncef
Liu, Qingshan
author_facet Yu, Li
Zhao, Yingbo
Wu, Shiyu
Yu, Siyue
Gabbouj, Moncef
Liu, Qingshan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_16137
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Degradation-Aware Hierarchical Termination for Blind Quality Enhancement of Compressed Video
Yu, Li
Zhao, Yingbo
Wu, Shiyu
Yu, Siyue
Gabbouj, Moncef
Liu, Qingshan
Computer Vision and Pattern Recognition
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.
title Degradation-Aware Hierarchical Termination for Blind Quality Enhancement of Compressed Video
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.16137