Satellite Image Super-Resolution Using Generative Adversarial Networks (GANs)

Abstract

Abstract: High-resolution satellite imagery is vital for applications such as environmental monitoring, urban planning, and defense. However, the availability of such data is limited by sensor constraints and acquisition costs. This paper investigates the use of Generative Adversarial Networks (GANs) to enhance the resolution of satellite images, using low-resolution input and learning to generate high-quality details. We explore and evaluate three GAN variants—SRGAN, ESRGAN, and WDSR-GAN—on two publicly available datasets: SpaceNet and UC Merced. Quantitative results indicate that ESRGAN achieves the highest performance, with a Peak Signal-to-Noise Ratio (PSNR) of 28.7 dB and Structural Similarity Index (SSIM) of 0.91. Regression and visual fidelity analysis confirm its robustness across diverse landscapes, showing its potential for improving satellite image usability. Keywords: satellite imagery, super-resolution, GANs, SRGAN, ESRGAN, WDSR, PSNR, SSIM, SpaceNet, UC Merced, deep learning