Nonpairwise-Trained Cycle Convolutional Neural Network for Single Remote Sensing Image Super-Resolution

Single image super-resolution (SISR) is to recover the high spatial resolution image from a single low spatial resolution one, which is a useful procedure for many remote sensing applications. Most previous convolutional neural network (CNN)-based methods adopt supervised learning. However, paired high-resolution and low-resolution remote sensing images are actually hard to acquire for supervised learning SR methods. To handle this problem, we propose a novel cycle convolutional neural network (Cycle-CNN). Our network consists of two generative CNNs for down-sampling and SR separately and can be trained with unpaired data. We perform comprehensive experiments on panchromatic and multispectral images of the GaoFen-2 satellite and the UC Merced land use data set. Experimental results indicate that our method achieves state-of-the-art CNN-based SR results and is robust against noise and blur in remote sensing images. Comprehensively considering super-resolved image quality and time costs, our proposed method outperforms the compared learning-based SISR approaches.