mlsanityData to 7 Oct 2026

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

arXiv 2603.14074 ↗First posted 14 Mar 2026cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 39 of its 52 references that are in the map. First posted on arXiv 14 Mar 2026.

Builds on

39 of 52 references.

References · 39

  1. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  2. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  3. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  4. 2022Diffusion Posterior Sampling for General Noisy Inverse Problemscited by 1,375
  5. 2022Denoising Diffusion Restoration Modelscited by 951
  6. 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 903
  7. 2021A Survey of Uncertainty in Deep Neural Networkscited by 675
  8. 2018Accurate Uncertainties for Deep Learning Using Calibrated Regressioncited by 417
  9. 2018Noise2Void - Learning Denoising from Single Noisy Imagescited by 359
  10. 2019Noise2Self: Blind Denoising by Self-Supervisioncited by 274
  11. 2019High-Quality Self-Supervised Deep Image Denoisingcited by 161
  12. 2015Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inferencecited by 159
27 more
  1. 2019Noisier2Noise: Learning to Denoise from Unpaired Noisy Datacited by 125
  2. 2021Noise2Score: Tweedie's Approach to Self-Supervised Image Denoising without Clean Imagescited by 110
  3. 2023Ambient Diffusion: Learning Clean Distributions from Corrupted Datacited by 108
  4. 2022Image-to-Image Regression with Distribution-Free Uncertainty Quantification and Applications in Imagingcited by 107
  5. 2021DEUP: Direct Epistemic Uncertainty Predictioncited by 102
  6. 2022A Deeper Look into Aleatoric and Epistemic Uncertainty Disentanglementcited by 87
  7. 2021Equivariant Imaging: Learning Beyond the Range Spacecited by 83
  8. 2021Uncertainty Toolbox: an Open-Source Library for Assessing, Visualizing, and Improving Uncertainty Quantificationcited by 57
  9. 2019Probabilistic Noise2Void: Unsupervised Content-Aware Denoisingcited by 51
  10. 2018Unsupervised Learning with Stein's Unbiased Risk Estimatorcited by 47
  11. 2018Training Deep Learning Based Denoisers without Ground Truth Datacited by 43
  12. 2024Rethinking Aleatoric and Epistemic Uncertaintycited by 40
  13. 2018Structured Uncertainty Prediction Networkscited by 34
  14. 2018Model-blind Video Denoising Via Frame-to-frame Trainingcited by 34
  15. 2022A theoretical framework for self-supervised MR image reconstruction using sub-sampling via variable density Noisier2Noisecited by 29
  16. 2023UnCRtainTS: Uncertainty Quantification for Cloud Removal in Optical Satellite Time Seriescited by 28
  17. 2023Sources of Uncertainty in Supervised Machine Learning -- A Statisticians' Viewcited by 27
  18. 2020Self-Supervised training for blind multi-frame video denoisingcited by 26
  19. 2021Permutation invariance and uncertainty in multitemporal image super-resolutioncited by 18
  20. 2023Equivariant Bootstrapping for Uncertainty Quantification in Imaging Inverse Problemscited by 17
  21. 2024UNSURE: self-supervised learning with Unknown Noise level and Stein's Unbiased Risk Estimatecited by 16
  22. 2020ENSURE: A General Approach for Unsupervised Training of Deep Image Reconstruction Algorithmscited by 13
  23. 2022WPPNets and WPPFlows: The Power of Wasserstein Patch Priors for Superresolutioncited by 10
  24. 2022Self-Supervised Super-Resolution for Multi-Exposure Push-Frame Satellitescited by 8
  25. 2026Self-Supervised Learning from Noisy and Incomplete Datacited by 5
  26. 2024Unsupervised Microscopy Video Denoisingcited by 2
  27. 2025An Analysis of Temporal Dropout in Earth Observation Time Series for Regression Taskscited by 2

Built on by

Not cited yet.