Volume IV-1
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., IV-1, 5-11, 2018
https://doi.org/10.5194/isprs-annals-IV-1-5-2018
© Author(s) 2018. This work is distributed under
the Creative Commons Attribution 4.0 License.
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., IV-1, 5-11, 2018
https://doi.org/10.5194/isprs-annals-IV-1-5-2018
© Author(s) 2018. This work is distributed under
the Creative Commons Attribution 4.0 License.

  26 Sep 2018

26 Sep 2018

SAR TO OPTICAL IMAGE SYNTHESIS FOR CLOUD REMOVAL WITH GENERATIVE ADVERSARIAL NETWORKS

J. D. Bermudez1, P. N. Happ1, D. A. B. Oliveira2, and R. Q. Feitosa1,3 J. D. Bermudez et al.
  • 1Pontifical Catholic University of Rio de Janeiro, Brazil
  • 2IBM Research
  • 3Rio de Janeiro State University, Brazil

Keywords: Cloud Removal, Conditional Generative Adversarial Networks, Deep Learning, Multispectral Images, SAR

Abstract. Optical imagery is often affected by the presence of clouds. Aiming to reduce their effects, different reconstruction techniques have been proposed in the last years. A common alternative is to extract data from active sensors, like Synthetic Aperture Radar (SAR), because they are almost independent on the atmospheric conditions and solar illumination. On the other hand, SAR images are more complex to interpret than optical images requiring particular handling. Recently, Conditional Generative Adversarial Networks (cGANs) have been widely used in different image generation tasks presenting state-of-the-art results. One application of cGANs is learning a nonlinear mapping function from two images of different domains. In this work, we combine the fact that SAR images are hardly affected by clouds with the ability of cGANS for image translation in order to map optical images from SAR ones so as to recover regions that are covered by clouds. Experimental results indicate that the proposed solution achieves better classification accuracy than SAR based classification.