A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is
In this paper, we propose a method for cloud removal from visible light RGB satellite images by extending the conditional Generative Adversarial Networks (cGANs) from RGB images to multispectral images ... Therefore, we propose a network that can remove clouds and generate visible light images from the multispectral images taken as inputs. ... In this paper, we propose Multispectral conditional Generative Adversarial Networks (McGANs) based on conditional Generative Adversarial Networks cGANs), for cloud removal from visible light RGB satellite ...doi:10.1109/cvprw.2017.197 dblp:conf/cvpr/EnomotoSWFMNK17 fatcat:2gomzyjdkjdv5n72c7ndcqtio4
In contrast, we cast the problem of cloud removal as a conditional image synthesis challenge, and we propose a trainable spatiotemporal generator network (STGAN) to remove clouds. ... We demonstrate experimentally that the proposed STGAN model outperforms standard models and can generate realistic cloud-free images with high PSNR and SSIM values across a variety of atmospheric conditions ... Using both the synthetic data and the original images' near infrared (NIR) channel, they train a Multispectral conditional Generative Adversarial Network (MC-GAN) to generate cloud-free images. ...arXiv:1912.06838v1 fatcat:4yap62zm3rf3xmnfuqtclxdbbu
Both approaches are evaluated experimentally, with their respective models trained and tested on SEN12MS-CR-TS. ... This work addresses the challenge of optical satellite image reconstruction and cloud removal by proposing a novel multimodal and multitemporal data set called SEN12MS-CR-TS. ... Related Work As the presence of clouds in optical satellite imagery poses a severe hindrance for remote-sensing applications, there has been plenty of preceding research on cloud removal methods  , ...doi:10.1109/tgrs.2022.3146246 fatcat:wqf63lrhsfae7hgwbm6tvlhkwe