PnP-CM: Consistency Models as Plug-and-Play Priors for Inverse Problems

arXiv:2509.22736v2 Announce Type: replace-cross Abstract: Diffusion models have found extensive use in solving inverse problems, by sampling from an approximate posterior distribution of data given the measurements. Recently, consistency models (CMs) have been proposed to directly predict the final output from any point on the diffusion ODE trajectory, enabling high-quality sampling in just a few neural function evaluations (NFEs). CMs have also been utilized for inverse problems, but existing C