On The Role of Alias and Band-Shift for Sentinel-2 Super-Resolution - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

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.
Fichier principal
Vignette du fichier
igarss2023_sentinel2_super_resolution.pdf (321.16 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04136470 , version 1 (21-06-2023)

Identifiants

Citer

Ngoc Long Nguyen, Jérémy Anger, Lara Raad, Bruno Galerne, Gabriele Facciolo. On The Role of Alias and Band-Shift for Sentinel-2 Super-Resolution. 2023 International Geoscience and Remote Sensing Symposium (IGARSS 2023), Jul 2023, Pasadena, United States. pp.4294-4297, ⟨10.1109/IGARSS52108.2023.10282805⟩. ⟨hal-04136470⟩
50 Consultations
41 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More