You can set up the environment using the environment.yml (the requirement is the same as [DDRM]: https://github.com/bahjat-kawar/ddrm). Run conda env create -f ...

Abstract: In recent years, the ascendance of diffusion modeling as a state-of-the-art generative modeling approach has spurred significant interest in their use as priors in Bayesian inverse problems.

Existing diffusion-based methods for inverse problems sample from the posterior using score functions and accept the generated random samples as solutions. In applications that posterior mean is ...