Priors are essential for reconstructing images from noisy and/or incomplete measurements. The choice of the prior determines both the quality and uncertainty of recovered images. We propose turning score-based diffusion models into principled image priors ("score-based priors") for analyzing a posterior of images given measurements. Previously, probabilistic priors were limited to handcrafted regularizers and simple distributions. In this work, we empirically validate the theoretically-proven probability function of a score-based diffusion model. We show how to sample from resulting posteriors by using this probability function for variational inference. Our results, including experiments on denoising, deblurring, and interferometric imaging, suggest that score-based priors enable principled inference with a sophisticated, data-driven image prior.
@article{arxiv.2304.11751,
title = {Score-Based Diffusion Models as Principled Priors for Inverse Imaging},
author = {Berthy T. Feng and Jamie Smith and Michael Rubinstein and Huiwen Chang and Katherine L. Bouman and William T. Freeman},
journal= {arXiv preprint arXiv:2304.11751},
year = {2023}
}