Multi-Spectral Multi-Image Super-Resolution of Sentinel-2 with Radiometric Consistency Losses and Its Effect on Building Delineation
This work addresses the need for affordable high-resolution imagery for social good applications, such as building detection, by leveraging multiple low-resolution images, but it is incremental as it extends existing MISR methods to multi-spectral remote sensing data.
The paper tackled the problem of generating high-resolution remote sensing imagery from freely available low-resolution Sentinel-2 data by applying multi-image super-resolution (MISR) with a radiometric consistency module, showing that MISR outperforms single-image super-resolution and other baselines on image fidelity metrics and improves building delineation performance.
High resolution remote sensing imagery is used in broad range of tasks, including detection and classification of objects. High-resolution imagery is however expensive, while lower resolution imagery is often freely available and can be used by the public for range of social good applications. To that end, we curate a multi-spectral multi-image super-resolution dataset, using PlanetScope imagery from the SpaceNet 7 challenge as the high resolution reference and multiple Sentinel-2 revisits of the same imagery as the low-resolution imagery. We present the first results of applying multi-image super-resolution (MISR) to multi-spectral remote sensing imagery. We, additionally, introduce a radiometric consistency module into MISR model the to preserve the high radiometric resolution of the Sentinel-2 sensor. We show that MISR is superior to single-image super-resolution and other baselines on a range of image fidelity metrics. Furthermore, we conduct the first assessment of the utility of multi-image super-resolution on building delineation, showing that utilising multiple images results in better performance in these downstream tasks.