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

• URL: http://arxiv.org/abs/2508.00721v1
• Date: Fri, 01 Aug 2025 15:40:37 GMT
• Title: FMPlug: Plug-In Foundation Flow-Matching Priors for Inverse Problems
• Authors: Yuxiang Wan, Ryan Devera, Wenjie Zhang, Ju Sun,
• Abstract summary: We present FMPlug, a novel plug-in framework that enhances foundation flow-matching (FM) priors.<n>Unlike traditional approaches that rely on domain-specific or untrained priors, FMPlug smartly leverages two simple but powerful insights.
• Score: 6.3140989721044445
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Measurement-aligned Flow for Inverse Problem [19.189110820948674]
  Measurement-Aligned Sampling (MAS) is a novel framework for linear inverse problem solving.<n>We show that MAS consistently outperforms state-of-the-art methods across a range of tasks.
  arXiv  Detail & Related papers  (2025-06-13T15:39:54Z)
• Diffusion prior as a direct regularization term for FWI [0.0]
  We propose a score-based generative diffusion prior into Full Waveform Inversion (FWI)<n>Unlike traditional diffusion approaches, our method avoids the reverse diffusion sampling and needs fewer iterations.<n>The proposed method offers enhanced fidelity and robustness compared to conventional and GAN-based FWI approaches.
  arXiv  Detail & Related papers  (2025-06-11T19:43:23Z)
• Solving Inverse Problems with FLAIR [59.02385492199431]
  Flow-based latent generative models are able to generate images with remarkable quality, even enabling text-to-image generation.<n>We present FLAIR, a novel training free variational framework that leverages flow-based generative models as a prior for inverse problems.<n>Results on standard imaging benchmarks demonstrate that FLAIR consistently outperforms existing diffusion- and flow-based methods in terms of reconstruction quality and sample diversity.
  arXiv  Detail & Related papers  (2025-06-03T09:29:47Z)
• Flow matching achieves almost minimax optimal convergence [50.38891696297888]
  Flow matching (FM) has gained significant attention as a simulation-free generative model. This paper discusses the convergence properties of FM for large sample size under the $p$-Wasserstein distance. We establish that FM can achieve an almost minimax optimal convergence rate for $1 leq p leq 2$, presenting the first theoretical evidence that FM can reach convergence rates comparable to those of diffusion models.
  arXiv  Detail & Related papers  (2024-05-31T14:54:51Z)
• Optimal Flow Matching: Learning Straight Trajectories in Just One Step [89.37027530300617]
  We develop and theoretically justify the novel textbf Optimal Flow Matching (OFM) approach. It allows recovering the straight OT displacement for the quadratic transport in just one FM step. The main idea of our approach is the employment of vector field for FM which are parameterized by convex functions.
  arXiv  Detail & Related papers  (2024-03-19T19:44:54Z)
• On Principled Local Optimization Methods for Federated Learning [2.628859872479184]
  dissertation aims to advance the theoretical foundation of local methods in the following three directions. First, we establish sharp bounds for FedAvg, the most popular algorithm in Federated Learning. Second, we propose Federated Accelerated Descent (FedAc), which provably improves the convergence rate and communication efficiency.
  arXiv  Detail & Related papers  (2024-01-24T03:57:45Z)
• GAFlow: Incorporating Gaussian Attention into Optical Flow [62.646389181507764]
  We push Gaussian Attention (GA) into the optical flow models to accentuate local properties during representation learning. We introduce a novel Gaussian-Constrained Layer (GCL) which can be easily plugged into existing Transformer blocks. For reliable motion analysis, we provide a new Gaussian-Guided Attention Module (GGAM)
  arXiv  Detail & Related papers  (2023-09-28T07:46:01Z)
• Training-free Linear Image Inverses via Flows [17.291903204982326]
  We propose a training-free method for solving linear inverse problems by using pretrained flow models. Our approach requires no problem-specific tuning across an extensive suite of noisy linear inverse problems on high-dimensional datasets.
  arXiv  Detail & Related papers  (2023-09-25T22:13:16Z)
• Poisson-Gaussian Holographic Phase Retrieval with Score-based Image Prior [19.231581775644617]
  We propose a new algorithm called "AWFS" that uses the accelerated Wirtinger flow (AWF) with a score function as generative prior. We calculate the gradient of the log-likelihood function for PR and determine the Lipschitz constant. We provide theoretical analysis that establishes a critical-point convergence guarantee for the proposed algorithm.
  arXiv  Detail & Related papers  (2023-05-12T18:08:47Z)
• A Variational Perspective on Solving Inverse Problems with Diffusion Models [101.831766524264]
  Inverse tasks can be formulated as inferring a posterior distribution over data. This is however challenging in diffusion models since the nonlinear and iterative nature of the diffusion process renders the posterior intractable. We propose a variational approach that by design seeks to approximate the true posterior distribution.
  arXiv  Detail & Related papers  (2023-05-07T23:00:47Z)
• NF-ULA: Langevin Monte Carlo with Normalizing Flow Prior for Imaging Inverse Problems [7.38079566297881]
  We introduce NF-ULA (Normalizing Flow-based Unadjusted Langevin algorithm), which involves learning a normalizing flow (NF) as the image prior. NF-ULA is found to perform better than competing methods for severely ill-posed inverse problems.
  arXiv  Detail & Related papers  (2023-04-17T15:03:45Z)
• Faster Adaptive Federated Learning [84.38913517122619]
  Federated learning has attracted increasing attention with the emergence of distributed data. In this paper, we propose an efficient adaptive algorithm (i.e., FAFED) based on momentum-based variance reduced technique in cross-silo FL.
  arXiv  Detail & Related papers  (2022-12-02T05:07:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.