[2304.11751] Score-Based Diffusion Models as Principled Priors for Inverse 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.

Score-Based Diffusion Models as Principled Priors for Inverse Imaging…

saved by

• Shayan Shekarforoush

related reading

• [2007.13640] Solving Linear Inverse Problems Using the Prior Implicit in a Denoiserarxiv.org
• Noise2Scoreproceedings.neurips.cc
• Regularized by Score Matching (LeCun)papers.nips.cc
• Denoising Density Estimatorsarxiv.org
• Unsupervised Learning with SURE.pdfarxiv.org
• Deep Energy Estimator.pdfarxiv.org
• Extending Stein's unbiased risk estimator to train deep denoisers with correlated pairs of noisy imagesproceedings.neurips.cc
• ML vs. Score matchingarxiv.org
• [2006.11239] Denoising Diffusion Probabilistic Modelsarxiv.org
• https://arxiv.org/pdf/2006.11239arxiv.org
• [2010.02502] Denoising Diffusion Implicit Modelsarxiv.org
• What are Diffusion Models?lilianweng.github.io