Diffusion Model Based Posterior Sampling for Noisy Linear Inverse Problems. (arXiv:2211.12343v1 [cs.LG] CROSS LISTED)

We consider the ubiquitous linear inverse problems with additive Gaussian
noise and propose an unsupervised general-purpose sampling approach called
diffusion model based posterior sampling (DMPS) to reconstruct the unknown
signal from noisy linear measurements. Specifically, the prior of the unknown
signal is implicitly modeled by one pre-trained diffusion model (DM). In
posterior sampling, to address the intractability of exact noise-perturbed
likelihood score, a simple yet effective noise-perturbed pseudo-likelihood
score is introduced under the uninformative prior assumption. While DMPS
applies to …

arxiv diffusion diffusion model linear posterior sampling