Evaluating Super-Resolution Models for Real-World Sentinel-2 Applications: A Case Study

Kurzfassung

High-resolution Earth observation data are crucial for applications such as agriculture, urban planning, and environmental monitoring.Although commercial satellites provide sub-meter imagery, open-access alternatives like Sentinel-2 are limited to resolutions around10 m ground sampling distance, which is insufficient for many tasks. In this work, we investigate image super-resolution as a methodto bridge this gap, enhancing downstream performance on freely available satellite data. We leverage two 16-bit single-band datasets,consisting of Sentinel-2 (20 m→10 m) and VENμS (10 m→5 m) images, to train and benchmark state-of-the-art SR methods,including transformer- and diffusion-based approaches, across multiple dataset mixes. These models are evaluated quantitativelyusing reference-based metrics (PSNR, SSIM) using ground-truth and no-reference scores (FID, NIQE) for native upscaling from20 m→10 m and 10 m→5 m. We observe that different SR architectures present trade-offs between standard quantitative metrics andperceptual image quality. We further assess their impact on a practical downstream task: field boundary detection from Sentinel-2imagery. Our experiments demonstrate that SR pre-processing improves quantitative fidelity and downstream task performance,enabling low-resolution satellites to compete more effectively with commercial imagery.