Towards Deep Unsupervised SAR Despeckling with Blind-Spot Convolutional Neural Networks

SAR despeckling is a problem of paramount importance in remote sensing, since it represents the first step of many scene analysis algorithms. Recently, deep learning techniques have outperformed classical model-based despeckling algorithms. However, such methods require clean ground truth images for...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2020-01
Hauptverfasser:	Andrea Bordone Molini, Valsesia, Diego, Fracastoro, Giulia, Magli, Enrico
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Artificial neural networks Ground truth Image acquisition Machine learning Noise reduction Remote sensing Scene analysis Synthetic aperture radar Training
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!