Dynamic degradation learning for real-world image super-resolution

Deep learning-based image super-resolution (SR) methods typically require high-resolution (HR) and corresponding low-resolution (LR) images to train SR networks. Since it is difficult to capture paired LR–HR images of exactly same scene from real world, most methods construct the training dataset by...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Signal, image and video processing image and video processing, 2023-03, Vol.17 (2), p.315-322
Hauptverfasser:	Fan, Chunxiao, Wu, Qiong, Ye, Xiang
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Imaging Computer Science Datasets Deep learning Degradation Image Processing and Computer Vision Image resolution Kernels Multimedia Information Systems Original Paper Pattern Recognition and Graphics Sampling Signal,Image and Speech Processing Training Vision
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!