Video Super-Resolution Using Non-Simultaneous Fully Recurrent Convolutional Network

Video super-resolution (SR) aims at restoring fine details and enhancing visual experience for low-resolution videos. In this paper, we propose a very deep non-simultaneous fully recurrent convolutional network for video SR. To make full use of temporal information, we employ motion compensation, ve...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on image processing 2019-03, Vol.28 (3), p.1342-1355
Hauptverfasser:	Li, Dingyi, Liu, Yu, Wang, Zengfu
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial neural networks Computer architecture Convolutional codes Image resolution Image restoration model ensemble Motion compensation non-simultaneous Quality assessment recurrent convolutional network residual connection State of the art Video super-resolution Visualization
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!