Title
SAQENet: A Quality Enhancement Network for Compressed Video with Self-attention
Abstract
Existing block-based encoding frameworks often use inaccurate quantification and motion compensation techniques, which result in many compression artifacts due to the loss of high-frequency information. In particular, the blurring of content edges and significant compression distortion can negatively impact the subjective video quality given limited coding resources. Hence, there is an urgent need to build a quality enhancement method for improving the quality of the compressed video at the receiving end given the same coding resources.
Year
DOI
Venue
2022
10.1109/DCC52660.2022.00096
2022 Data Compression Conference (DCC)
Keywords
DocType
ISSN
subjective video quality,coding resources,quality enhancement method,compressed video,SAQENet,quality enhancement network,existing block-based,inaccurate quantification,motion compensation techniques,compression artifacts,high-frequency information,content edges,significant compression distortion
Conference
1068-0314
ISBN
Citations 
PageRank 
978-1-6654-7894-6
0
0.34
References 
Authors
0
4
Name
Order
Citations
PageRank
Xuan Sun100.34
Pengyu Liu200.34
Bin Jiang312.38
Shanji Chen400.34