New architecture of deep recursive convolution networks for super-resolution

More existing methods of single image super-resolution (SR) often direct super-resolving the details, but when the upsampling factor is larger, it is challenging to reconstruct high-frequency details. Lately, deep convolution neural networks have made significant progress with regard to SR. However,...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Knowledge-based systems 2019-08, Vol.178, p.98-110
Hauptverfasser:	Cao, Feilong, Chen, Baijie
Format:	Artikel
Sprache:	eng
Schlagworte:	Architecture Artificial neural networks Concrete blocks Convolution Convolution neural networks Deep learning Feature extraction Image reconstruction Image resolution Neural networks Recursive methods Recursive networks Residual-feature learning Super-resolution Training
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!