UNSUPERVISED REMOTE SENSING IMAGE SUPER-RESOLUTION USING CYCLE CNN

Single image super-resolution (SISR) is a useful procedure for many remote sensing applications. However, paired high-resolution and low-resolution remote sensing images are actually hard to acquire for supervised learning SR methods. In this paper, we propose an unsupervised network named Cycle-CNN to handle this problem. Our network consists of two generative CNNs for down-sampling and super-resolution separately, and can be trained with unpaired data. Experiments on panchromatic and multi-spectral images of GaoFen-2 satellite indicate that our method achieves state-of-the-art SR results and is robust against noise and blur in the remote sensing images.