Image Super Resolution for Satellite Imagery

Abstract

Super resolution (SR) techniques play a critical role in enhancing the quality of satellite imagery by reconstructing high resolution (HR) images from low resolution (LR) inputs. This study investigates the application of the Enhanced Super Resolution Generative Adversarial Network (ESRGAN) to improve the spatial resolution of satellite images. The ESRGAN framework integrates a Residual-in-Residual Dense Block (RRDB) generator, a Relativistic average GAN (RaGAN) discriminator, and an improved perceptual loss function to achieve sharper textures and more realistic structures. The 4× Satellite Image Super Resolution dataset, consisting of paired LR (2 m/pixel) and HR (0.5 m/pixel) images, was employed. Quantitative evaluation was conducted using the Peak Signal-to-Noise Ratio (PSNR), with Lanczos5 interpolation used as a baseline for comparison. Experimental results on ten test images demonstrate that ESRGAN consistently outperforms Lanczos5. Qualitative assessments further confirm that ESRGAN effectively restores high frequency details, enhances fine textures, and preserves object boundaries more accurately than the interpolation method. These findings highlight ESRGAN’s potential as an advanced solution for improving visual quality and detail preservation in high resolution satellite imagery applications.