Self-Supervised Uncertainty Estimation For Super-Resolution of Satellite Images

TL;DR

This paper introduces a self-supervised method for satellite image super-resolution that estimates uncertainty without ground-truth data, using a Bayesian risk minimization approach validated on synthetic datasets.

Contribution

It presents a novel self-supervised loss for uncertainty estimation in super-resolution, bridging the gap between self-supervised restoration and uncertainty quantification.

Findings

Produces calibrated uncertainty estimates comparable to supervised methods

Validates approach on synthetic SkySat dataset

Provides a practical framework for uncertainty-aware image reconstruction

Abstract

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.