Frequency-Conditioned GAN for Remote Sensing Image Super-Resolution
Remote sensing image super-resolution aims to recover fine spatial details lost during image acquisition, yet most existing deep learning methods often struggle to faithfully reconstruct high-frequency details and maintain spectral fidelity. To address these limitations, we build FC-GAN, a frequency-conditioned model that adapts frequency separation techniques to remote sensing data. FC-GAN employs a frequency-aware supervision approach that explicitly enforces consistency between the reconstructed outputs and the frequency characteristics of the original scene, ensuring that the synthesized textures and fine-scale spatial structures align with the ground-truth spatial power spectrum. In addition to spatial-domain metrics, we extend the standard frequency-domain evaluation framework from the meteorological downscaling literature to assess spectral fidelity using the radially averaged power spectral density (RAPSD) and log-spectral distance (RALSD). Experiments on three remote sensing datasets for $\times 4$ upsampling demonstrate that FC-GAN improves reconstruction quality and better preserves frequency-domain statistics. The source code and model weights are publicly available at https://github.com/victor-nasc/FC-GAN