Score-Based Diffusion Models as Principled Priors for Inverse Imaging
This work addresses the need for sophisticated, data-driven priors in inverse imaging, offering a principled approach for researchers and practitioners in computational imaging.
The paper tackled the problem of reconstructing images from noisy or incomplete measurements by proposing score-based diffusion models as principled priors, enabling improved inference in tasks like denoising, deblurring, and interferometric imaging.
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.