Saving Foundation Flow-Matching Priors for Inverse Problems

Foundation flow-matching (FM) models promise universal priors for solving inverse problems (IPs); yet today, they trail behind domain-specific and even untrained priors. \emph{How can we unlock their potential?} We introduce FMPlug, a plug-in framework that redefines how foundation FMs are used in IPs. FMPlug combines an instance-guided, time-dependent warm-start strategy with sharp Gaussianity regularization, adding problem-specific guidance while preserving the Gaussian structures. For evaluation, we consider both simple image restoration tasks and scientific IPs with a few similar samples---where the prohibitive cost of data collection and model training hinders the development of domain-specific generative models. Our superior experimental results confirm the effectiveness of FMPlug. Overall, FMPlug paves the way for making foundation FM models practical, reusable priors for IPs, especially scientific ones with few similar samples.

Foundation models excel at general image generation, however, adapting them to solve complex inverse problems—ranging from image restoration to specialized scientific imaging—remains a major challenge. We developed FMPlug, a framework that leverages an instance-guided "warm-start" strategy to enhance general image restoration capabilities. In scientific domain, by utilizing just a few sample instances, FMPlug successfully guides general foundation models toward accurate solutions for scientific inverse problems without requiring unavailable domain-specific models. FMPlug paves the way for making general foundation models practical, reusable priors for inverse problems.