cs.LGNov 10, 2026

Plug-and-Play ADMM for Inverse Problems with Flow Matching Denoiser

Authors: Dibyanshu Kumar, Magda Gregorova

Organizations: TH Würzburg-Schweinfurt, CAIRO · University of Würzburg

Abstract

Plug-and-Play (PnP) methods with generative priors have achieved strong performance in inverse problems, with recent flow matching models enabling fast and scalable reconstruction. However, a key challenge in PnP methods is maintaining consistency between data fidelity updates and the learned generative prior, as data-consistency steps can move iterates away from the flow trajectory. We propose an ADMM-based PnP framework for flow matching priors that enforces stronger consistency between the measurement model and the prior through auxiliary variables and dual updates. In addition, we introduce a trajectory correction mechanism that restores consistency with the flow via a combination of deterministic and stochastic projections. Our method provides a more principled integration of flow priors within PnP frameworks, achieving high-quality reconstructions with reduced computational cost.

Figures & tables

Appendix figures & tables11 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. FlowADMM: Plug-and-play ADMM with Flow-based Renoise-Denoise Priors

    May 9, 2026Hendrik Sommerhoff, Michael MoellerAlternating Direction Method of MultipliersImage Restoration

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

    Oct 19, 2026Dibyanshu Kumar, Magda GregorovaInverse ProblemsFlow Matching

  3. AdjointFlow: Accelerating Scientific Inverse Problems with Physics-Based Transport

    Nov 10, 2026Ethan Hanold, Nicholas M. Boffi, Qin Li +1Inverse ProblemsPhysics-Informed Generative Modeling