Superresolving Sentinel-2 Using Learned Multispectral Regularization

The Sentinel-2 (S2) satellite constellation provides images at three different spatial resolutions and model based superresolution methods have proved useful for sharpening them to their maximum resolution. Algorithm unrolling is a way of building efficient, interpretable neural networks by reimplem...

Full description

Saved in:
Bibliographic Details
Main Authors: Armannsson, Sveinn E., Ulfarsson, Magnus O., Sveinsson, Johannes R., Sigurdsson, Jakob
Format: Conference Proceeding
Language:English
Subjects:
Buildings
Geoscience and remote sensing
Image color analysis
Image sharpening
multispectral (MS) multiresolution images
Neural networks
Satellite constellations
Sentinel-2
Superresolution
Training
unrolling
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The Sentinel-2 (S2) satellite constellation provides images at three different spatial resolutions and model based superresolution methods have proved useful for sharpening them to their maximum resolution. Algorithm unrolling is a way of building efficient, interpretable neural networks by reimplementing traditional algorithms in a neural network context. In this paper, an unrolled model based method to superresolve S2 images is proposed and unsupervised single image training is performed using reduced scale data. The method is evaluated using both real and simulated data.
ISSN:2153-7003
DOI:10.1109/IGARSS52108.2023.10281544