Authors:
Morui Zhu
1
;
Chang Liu
2
;
1
and
Tamás Szirányi
2
;
3
Affiliations:
1
Department of Networked Systems and Services, Budapest University of Technology and Economics, BME Informatika épület Magyar tudósok körútja 2, Budapest, Hungary
;
2
Machine Perception Research Laboratory of Institute for Computer Science and Control (SZTAKI), H-1111 Budapest, Kende u. 13-17, Hungary
;
3
Faculty of Transportation Engineering and Vehicle Engineering, Budapest University of Technology and Economics (BME-KJK), Műegyetem rkp. 3., Budapest, H-1111, Hungary
Keyword(s):
Cloud, Cloud Shadow Removal, Generative Adversarial Networks, Spatio-Temporal, Sentinel-2.
Abstract:
Due to the inevitable contamination of thick clouds and their shadows, satellite images are greatly affected, which significantly reduces the usability of data from satellite images. Therefore, obtaining high-quality image data without cloud contamination in a specific area and at the time we need it is an important issue. To address this problem, we collected a new multi-temporal dataset covering the entire globe, which is used to remove clouds and their shadows. Since generative adversarial networks (GANs) perform well in conditional image synthesis challenges, we utilized a spatial-temporal GAN (STGAN) to eliminate clouds and their shadows in optical satellite images. As a baseline model, STGAN demonstrated outstanding performance in peak signalto-noise ratio (PSNR) and structural similarity index (SSIM), achieving scores of 33.4 and 0.929, respectively. The cloud-free images generated in this work have significant utility for various downstream applications in real-world environm
ents. Dataset is publicly available: https://github.com/zhumorui/SMT-CR
(More)