Self-Supervised Uncertainty Estimation For Super-Resolution of Satellite Images
This work provides a practical framework for uncertainty-aware image reconstruction in satellite imagery, addressing a gap in self-supervised methods, though it is incremental as it builds on existing self-supervised SR techniques.
The paper tackles the problem of uncertainty estimation in self-supervised super-resolution of satellite images, where paired data is unavailable, and demonstrates that their method produces calibrated uncertainty estimates comparable to supervised approaches on a synthetic dataset.
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.