FMPlug: Plug-In Foundation Flow-Matching Priors for Inverse Problems

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wan, Yuxiang, Devera, Ryan, Zhang, Wenjie, Sun, Ju
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912727208820736
author Wan, Yuxiang
Devera, Ryan
Zhang, Wenjie
Sun, Ju
author_facet Wan, Yuxiang
Devera, Ryan
Zhang, Wenjie
Sun, Ju
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_00721
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FMPlug: Plug-In Foundation Flow-Matching Priors for Inverse Problems
Wan, Yuxiang
Devera, Ryan
Zhang, Wenjie
Sun, Ju
Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
Signal Processing
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.
title FMPlug: Plug-In Foundation Flow-Matching Priors for Inverse Problems
topic Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
Signal Processing
url https://arxiv.org/abs/2508.00721