<ul><li>A new framework for uncertainty quantification in computational imaging has been introduced.</li><li>The proposed framework combines generative model-based methods and Bayesian neural networks.</li><li>The framework can jointly quantify aleatoric and epistemic uncertainties in image reconstruction.</li><li>Experiments on different imaging problems demonstrate the effectiveness and calibration of the proposed framework.</li></ul>

Conformalized Generative Bayesian Imaging: An Uncertainty Quantification Framework for Computational Imaging

Discover more