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

2026-09-17

AI Summary

本文提出FlowSGS方法，通过结合Split Gibbs Sampling和Stochastic Interpolants改进了基于流匹配的逆成像问题求解，尤其适用于非线性模型。

Abstract

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 Interpolants (SI) framework to integrate a pretrained flow model into the prior step. We provide a form for the prior step that uses SI's reverse-time SDE, and show connections to previous PnP methods. Moreover, with the aid of the flow prior's straight probability paths and a novel timestep correction technique for the reverse-time SDE, FlowSGS requires fewer network evaluations in its prior step than plug-and-play diffusion samplers. Our experiments show state-of-the-art performance on a range of inverse problems. For the first time, we provide an experiment on a nonlinear inverse problem (Fourier phase retrieval) for flow-based inverse solvers.

Problem

• Flow Matching
• Inverse Imaging
• Stochastic Interpolants
• Posterior Sampling
• Nonlinear Inverse Problems

Innovation

• FlowSGS
• Split Gibbs Sampling
• Stochastic Interpolants
• Langevin dynamics
• reverse-time SDE