ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume V-3-2022
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., V-3-2022, 591–596, 2022
https://doi.org/10.5194/isprs-annals-V-3-2022-591-2022
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., V-3-2022, 591–596, 2022
https://doi.org/10.5194/isprs-annals-V-3-2022-591-2022
 
17 May 2022
17 May 2022

SUPER RESOLUTION FOR SINGLE SATELLITE IMAGE USING A GENERATIVE ADVERSARIAL NETWORK

R. Li1, W. Liu1, W. Gong2, X. Zhu1, and X. Wang1 R. Li et al.
  • 1National Geomatics Center of China
  • 2State Key Laboratory of Earthquake Dynamics, Institute of Geology, China Earthquake Administration, China

Keywords: Super Resolution, Satellite Imagery, Generative Adversarial Network, Residual Network

Abstract. Inspired by the immense success of deep neural network in image processing and object recognition, learning-based image super resolution (SR) methods have been highly valued and have become the mainstream direction of super resolution research. Base on the recent proposed state-of-art convolution neural network (CNN) super-resolution methods, this paper proposed a generative adversarial network for single satellite image Super Resolution reconstruction. It built on a trained deep residual network to generate preliminary SR images, combined with a discriminative network learns to differentiate preliminary SR images and High resolution samples. The experiments results show that our method can use existing model parameters to refine SR image performance.