The paper Cloud removal in Sentinel-2 imagery using a deep residual neural network and SAR-optical data fusion, authored by Andrea Meraner, Patrick Ebel, Xiao Xiang Zhu, and Michael Schmitt, has been selected as the best paper published in 2020 (volumes 159-170) in the ISPRS Journal of Photogrammetry and Remote Sensing.

The prize accompanying this award consists of a certificate and a one-year free subscription to the ISPRS Journal. The Award shall be presented to the recipients by the President of ISPRS and a representative of each sponsor at a plenary session of the Congress or an ISPRS conference event. As the best paper of 2020, the paper will also compete for the prestigious ISPRS U.V. Helava award for the period of 2020-2023. 

The work proposes a Residual Network for the purpose of cloud-removal in optical data via multi-spectral optical and SAR data fusion. Global and all-season Sentinel-1 and Sentinel-2 data is collected for training the network and experiments demonstrate the superiority of the proposed model over baselines, as well as its capability to remove even dense and in transparent clouds.

Reference: Meraner, A., Ebel, P., Zhu, X. X., & Schmitt, M. (2020). Cloud removal in Sentinel-2 imagery using a deep residual neural network and SAR-optical data fusion. ISPRS Journal of Photogrammetry and Remote Sensing, 166, 333-346. https://www.sciencedirect.com/science/article/pii/S0924271620301398
Code: https://github.com/ameraner/dsen2-cr
Data (updated): http://mediatum.ub.tum.de/1554803