Saved in:
Bibliographic Details
Main Authors: Zheng, Zhe, Dewil, Valéry, Arias, Pablo
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.14074
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911515873902592
author Zheng, Zhe
Dewil, Valéry
Arias, Pablo
author_facet Zheng, Zhe
Dewil, Valéry
Arias, Pablo
contents Super-resolution (SR) of satellite imagery is challenging due to the lack of paired low-/high-resolution data. Recent self-supervised SR methods overcome this limitation by exploiting the temporal redundancy in burst observations, but they lack a mechanism to quantify uncertainty in the reconstruction. In this work, we introduce a novel self-supervised loss that allows to estimate uncertainty in image super-resolution without ever accessing the ground-truth high-resolution data. We adopt a decision-theoretic perspective and show that minimizing the corresponding Bayesian risk yields the posterior mean and variance as optimal estimators. We validate our approach on a synthetic SkySat L1B dataset and demonstrate that it produces calibrated uncertainty estimates comparable to supervised methods. Our work bridges self-supervised restoration with uncertainty quantification, making a practical framework for uncertainty-aware image reconstruction.
format Preprint
id arxiv_https___arxiv_org_abs_2603_14074
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Self-Supervised Uncertainty Estimation For Super-Resolution of Satellite Images
Zheng, Zhe
Dewil, Valéry
Arias, Pablo
Computer Vision and Pattern Recognition
Machine Learning
Super-resolution (SR) of satellite imagery is challenging due to the lack of paired low-/high-resolution data. Recent self-supervised SR methods overcome this limitation by exploiting the temporal redundancy in burst observations, but they lack a mechanism to quantify uncertainty in the reconstruction. In this work, we introduce a novel self-supervised loss that allows to estimate uncertainty in image super-resolution without ever accessing the ground-truth high-resolution data. We adopt a decision-theoretic perspective and show that minimizing the corresponding Bayesian risk yields the posterior mean and variance as optimal estimators. We validate our approach on a synthetic SkySat L1B dataset and demonstrate that it produces calibrated uncertainty estimates comparable to supervised methods. Our work bridges self-supervised restoration with uncertainty quantification, making a practical framework for uncertainty-aware image reconstruction.
title Self-Supervised Uncertainty Estimation For Super-Resolution of Satellite Images
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2603.14074