SOURCE-LINKED INTELLIGENCE

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

arXiv · AI, language, vision and robotics · article · Sep 17, 2026 · UTC

Flow matching has emerged as the state-of-the-art generative model and has been used for plug-and-play (PnP) priors to solve inverse problems in computational imaging. However, existing flow-based inverse solvers assume linear forward models and/or make simplifying approximations in posterior sampling. To circumvent these problems, we introduce FlowSGS, a flow-based posterior sampling method using Split Gibbs Sampling (SGS) to decompose the posterior into a likelihood step and a prior step. Specifically, we sample from the likelihood step using Langevin dynamics and leverage the Stochastic Int

Read original source ↗ Open in workspace

recordType

paper

region

Global