Saving Foundation Flow-Matching Priors for Inverse Problems

Yuxiang Wan, Ryan Devera, Wenjie Zhang, Ju Sun
11/20/2025
cs.LGcs.CVeess.IV

No confident code implementation found for this paper. 1 possible match can be shown below.

Abstract

Foundation flow-matching (FM) models promise a universal prior for solving inverse problems (IPs), yet today they trail behind domain-specific or even untrained priors. 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 a sharp Gaussianity regularization, adding problem-specific guidance while preserving the Gaussian structures. This leads to a significant performance boost across image restoration and scientific IPs. Our results point to a path for making foundation FM models practical, reusable priors for IP solving.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 1 weaker match is hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

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

96% match2025

DAWN-FM: Data-Aware and Noise-Informed Flow Matching for Solving Inverse Problems

81% match1 repo22024

Latent Refinement via Flow Matching for Training-free Linear Inverse Problem Solving

81% match2025

PnP-CF: A Consensus Flow-Matching Solver for General Inverse Problems

81% match2026

Consistency Models as Plug-and-Play Priors for Inverse Problems

80% match2025

Latent Riemannian Flow Matching for Geometry-Grounded 3D Foundation Models

80% match2026

Cite this paper

@article{wan2025saving,
  title  = {Saving Foundation Flow-Matching Priors for Inverse Problems},
  author = {Yuxiang Wan and Ryan Devera and Wenjie Zhang and Ju Sun},
  year   = {2025},
  eprint = {2511.16520},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2511.16520v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2511.16520.svg)](https://codeofpaper.com/paper/2511.16520)

Discussion