On The Role of Alias and Band-Shift for Sentinel-2 Super-Resolution
This addresses super-resolution for remote sensing data, but it is incremental as it applies existing deep-learning methods to a new dataset.
The paper tackles single-image super-resolution for Sentinel-2 imagery by leveraging its sensor specifications like inter-band shift and alias, achieving results free of hallucinated details using a simple L1 loss.
In this work, we study the problem of single-image super-resolution (SISR) of Sentinel-2 imagery. We show that thanks to its unique sensor specification, namely the inter-band shift and alias, that deep-learning methods are able to recover fine details. By training a model using a simple $L_1$ loss, results are free of hallucinated details. For this study, we build a dataset of pairs of images Sentinel-2/PlanetScope to train and evaluate our super-resolution (SR) model.