Diffusion Posterior Sampling for General Noisy Inverse Problems. (arXiv:2209.14687v1 [stat.ML])

Diffusion models have been recently studied as powerful generative inverse
problem solvers, owing to their high quality reconstructions and the ease of
combining existing iterative solvers. However, most works focus on solving
simple linear inverse problems in noiseless settings, which significantly
under-represents the complexity of real-world problems. In this work, we extend
diffusion solvers to efficiently handle general noisy (non)linear inverse
problems via the Laplace approximation of the posterior sampling.
Interestingly, the resulting posterior sampling scheme is a blended version …

arxiv diffusion general posterior sampling