Tianao Li

FlowSGS: Improving Flow Matching Priors for Inverse Imaging with Stochastic Interpolants

This work introduces FlowSGS, a flow-based posterior sampling method using Split Gibbs Sampling (SGS) to decompose the posterior into a likelihood step and a prior step and provides a form for the prior step that uses SI's reverse-time SDE, and shows connections to previous PnP methods.