GAN-Based Image Super-Resolution with a Novel Quality Loss

Single image super-resolution (SISR) has been a very attractive research topic in recent years. Breakthroughs in SISR have been achieved due to deep learning and generative adversarial networks (GANs). However, the generated image still suffers from undesired artifacts. In this paper, we propose a n...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Mathematical problems in engineering 2020, Vol.2020 (2020), p.1-12
Hauptverfasser:	Shen, Ying, Liu, Xiao, Zhang, Lijun, Zhang, Lin, Zhu, Xining, Zhao, Shengjie
Format:	Artikel
Sprache:	eng
Schlagworte:	Datasets Generative adversarial networks Image quality Image resolution Machine learning Mapping Quality Quality assessment Training Vision systems
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!