Real Sentinel-2 Super-Resolution: The Case for Misregistration-Aware Training Data

Read full text Summarise with VIRAT
Authors: Tomasz Tarasiewicz, Michał Kawulok
Cited by: 0
References: 18

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Preprint of a paper accepted to IGARSS 2026. This work identifies inter-band misregistration as a critical flaw in Sentinel-2 super-resolution training data and proposes a progressive simulation framework with a registration-aware graph neural network to address the domain gap.

Fields of Study & Subjects

Advanced Image Processing Techniques Satellite Image Processing and Photogrammetry Advanced Image Fusion Techniques

Publication details

Journal / source
IEEE International Geoscience and Remote Sensing Symposium (IGARSS)
Pages
2394–2398
Publication date
1 August 2026
Language
EN