On The Role of Alias and Band-Shift for Sentinel-2 Super-Resolution
Résumé
In this work, we study the problem of single-image superresolution (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.
| Origine | Fichiers produits par l'(les) auteur(s) |
|---|