Plug-and-Play ADMM for Inverse Problems with Flow Matching Denoiser
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.
Plug-and-Play ADMM with flow matching denoiser for inverse problems
- arXiv
- 2611.13742
- Authors
- Dibyanshu Kumar, Magda Gregorova
- Categories
- cs.LG