Saving Foundation Flow-Matching Priors for Inverse Problems

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Wan, Yuxiang, Devera, Ryan, Zhang, Wenjie, Sun, Ju
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909034492198912
author Wan, Yuxiang
Devera, Ryan
Zhang, Wenjie
Sun, Ju
author_facet Wan, Yuxiang
Devera, Ryan
Zhang, Wenjie
Sun, Ju
contents 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. More details are available at https://sun-umn.github.io/xm-plug/ .
format Preprint
id arxiv_https___arxiv_org_abs_2511_16520
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Saving Foundation Flow-Matching Priors for Inverse Problems
Wan, Yuxiang
Devera, Ryan
Zhang, Wenjie
Sun, Ju
Machine Learning
Computer Vision and Pattern Recognition
Image and Video Processing
Signal Processing
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. More details are available at https://sun-umn.github.io/xm-plug/ .
title Saving Foundation Flow-Matching Priors for Inverse Problems
topic Machine Learning
Computer Vision and Pattern Recognition
Image and Video Processing
Signal Processing
url https://arxiv.org/abs/2511.16520