Efficient Bayesian Computational Imaging with a Surrogate Score-Based Prior

Berthy Feng, Katherine Bouman

Keywords: computational imaging, inverse problems, generative priors

Abstract: We propose a surrogate function for efficient use of score-based priors for Bayesian inverse imaging. Recent work turned score-based diffusion models into probabilistic priors for solving ill-posed imaging problems by appealing to an ODE-based log-probability function. However, evaluating this function is computationally inefficient and inhibits posterior estimation of high-dimensional images. Our proposed surrogate prior is based on the evidence lower-bound of a score-based diffusion model. We demonstrate the surrogate prior on variational inference for efficient posterior sampling of large images. Compared to the exact prior used in previous work, our surrogate prior accelerates optimization of the variational distribution by at least two orders of magnitude. We also find that our principled approach achieves higher-fidelity image-reconstruction than non-Bayesian baselines that involve hyperparameter-tuning at inference. Our work establishes a practical path forward for using score-based diffusion models as general-purpose priors for computational imaging.

Submission Number: 8873