A Robust Quality Enhancement Method Based on Joint Spatial-Temporal Priors for Video Coding

Quality enhancement of HEVC compressed videos has attracted a lot of attentions in recent years. In this article, we propose a robust multi-frame guided attention network (MGANet) to reconstruct high-quality frames based on HEVC compressed videos. In our network, we first use an advanced motion flow...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on circuits and systems for video technology Jg. 31; H. 6; S. 2401 - 2414
Hauptverfasser:	Meng, Xiandong, Deng, Xuan, Zhu, Shuyuan, Zhang, Xinfeng, Zeng, Bing
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	New York IEEE 01.06.2021 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:	Algorithms Coders Coding ConvLSTM Encoders-Decoders Encoding Frame design Frames (data processing) guided attention High efficiency video coding (HEVC) Image coding Image reconstruction optical flow quality enhancement Robustness Transforms Video compression
ISSN:	1051-8215, 1558-2205
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!