Coarse-to-Fine CNN for Image Super-Resolution

Deep convolutional neural networks (CNNs) have been popularly adopted in image super-resolution (SR). However, deep CNNs for SR often suffer from the instability of training, resulting in poor image SR performance. Gathering complementary contextual information can effectively overcome the problem....

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on multimedia 2021, Vol.23, p.1489-1502
Hauptverfasser:	Tian, Chunwei, Xu, Yong, Zuo, Wangmeng, Zhang, Bob, Fei, Lunke, Lin, Chia-Wen
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial neural networks Cascaded structure convolutional neural network Distillation Feature extraction feature fusion feature refinement Fuses High resolution Image reconstruction Image resolution Image super-resolution Residual neural networks Training Visualization
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!