We present FMPlug, a novel plug-in framework that enhances foundation flow-matching (FM) priors for solving ill-posed inverse problems. Unlike traditional approaches that rely on domain-specific or untrained priors, FMPlug smartly leverages two simple but powerful insights: the similarity between observed and desired objects and the Gaussianity of generative flows. By introducing a time-adaptive warm-up strategy and sharp Gaussianity regularization, FMPlug unlocks the true potential of domain-agnostic foundation models. Our method beats state-of-the-art methods that use foundation FM priors by significant margins, on image super-resolution and Gaussian deblurring.
Cite
@article{arxiv.2508.00721,
title = {FMPlug: Plug-In Foundation Flow-Matching Priors for Inverse Problems},
author = {Yuxiang Wan and Ryan Devera and Wenjie Zhang and Ju Sun},
journal= {arXiv preprint arXiv:2508.00721},
year = {2025}
}