Cloud-EGAN: Rethinking CycleGAN From a Feature Enhancement Perspective for Cloud Removal by Combining CNN and Transformer

Cloud cover presents a major challenge for geoscience research of remote sensing images with thick clouds causing complete obstruction with information loss while thin clouds blurring the ground objects. Deep learning (DL) methods based on convolutional neural networks (CNNs) have recently introduce...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE journal of selected topics in applied earth observations and remote sensing 2023-01, Vol.16, p.1-14
Hauptverfasser:	Ma, Xianping, Huang, Yiming, Zhang, Xiaokang, Pun, Man-On, Huang, Bo
Format:	Artikel
Sprache:	eng
Schlagworte:	Aggregation Artificial neural networks Blurring Cloud cover Cloud removal Clouds Convolutional neural networks cycle-consistent generative adversarial network (CycleGAN) CycleGAN Deep learning feature enhancement Feature extraction Feature maps Generative adversarial networks Generators Information retrieval Machine learning Modules Neural networks Regeneration Remote sensing remote sensing images Removal transformer Transformers
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!