Beyond Pretty Pictures: Combined Single- and Multi-Image Super-resolution for Sentinel-2 Images
This addresses the need for higher-resolution Earth observation data for applications like urban mapping, though it is incremental as it builds on existing super-resolution methods.
The paper tackles the problem of low-resolution Sentinel-2 satellite images by developing SEN4X, a hybrid super-resolution architecture that combines single- and multi-image techniques to upgrade imagery to 2.5 m ground sampling distance, resulting in significant performance improvements in urban land-cover classification over state-of-the-art baselines.
Super-resolution aims to increase the resolution of satellite images by reconstructing high-frequency details, which go beyond naïve upsampling. This has particular relevance for Earth observation missions like Sentinel-2, which offer frequent, regular coverage at no cost; but at coarse resolution. Its pixel footprint is too large to capture small features like houses, streets, or hedge rows. To address this, we present SEN4X, a hybrid super-resolution architecture that combines the advantages of single-image and multi-image techniques. It combines temporal oversampling from repeated Sentinel-2 acquisitions with a learned prior from high-resolution Pléiades Neo data. In doing so, SEN4X upgrades Sentinel-2 imagery to 2.5 m ground sampling distance. We test the super-resolved images on urban land-cover classification in Hanoi, Vietnam. We find that they lead to a significant performance improvement over state-of-the-art super-resolution baselines.