Pith. sign in

REVIEW 6 cited by

PnP-Flow: Plug-and-Play Image Restoration with Flow Matching

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2410.02423 v3 pith:PKMEFJDS submitted 2024-10-03 cs.CV cs.LG

Ségolène Martin , Anne Gagneux , Paul Hagemann , Gabriele Steidl This is my paper · ORCID
classification cs.CVcs.LG
keywords flowmatchingimagealgorithmdenoisingefficientgenerativeimaging
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

In this paper, we introduce Plug-and-Play (PnP) Flow Matching, an algorithm for solving imaging inverse problems. PnP methods leverage the strength of pre-trained denoisers, often deep neural networks, by integrating them in optimization schemes. While they achieve state-of-the-art performance on various inverse problems in imaging, PnP approaches face inherent limitations on more generative tasks like inpainting. On the other hand, generative models such as Flow Matching pushed the boundary in image sampling yet lack a clear method for efficient use in image restoration. We propose to combine the PnP framework with Flow Matching (FM) by defining a time-dependent denoiser using a pre-trained FM model. Our algorithm alternates between gradient descent steps on the data-fidelity term, reprojections onto the learned FM path, and denoising. Notably, our method is computationally efficient and memory-friendly, as it avoids backpropagation through ODEs and trace computations. We evaluate its performance on denoising, super-resolution, deblurring, and inpainting tasks, demonstrating superior results compared to existing PnP algorithms and Flow Matching based state-of-the-art methods.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Solving Inverse Problems with Flow-based Models via Model Predictive Control

    eess.IV 2026-01 conditional novelty 6.0 of 10

    MPC-Flow applies model predictive control to guide pretrained flow models through inverse problems, with a single-step variant that avoids backpropagation and scales to 32B-parameter models on consumer hardware.

  2. PnP-DA: Towards Principled Plug-and-Play Integration of Variational Data Assimilation and Generative Models

    cs.LG 2025-08 conditional novelty 6.0 of 10

    PnP-DA combines a lightweight variational observation update with a pretrained conditional flow-matching denoiser to reduce analysis error in chaotic data assimilation, outperforming 3D-Var on Lorenz 63, Lorenz 96, an...

  3. FlowSteer: Conditioning Flow Field for Consistent Image Restoration

    eess.IV 2025-12 conditional novelty 5.0 of 10

    A sparse mid-to-late schedule of null-space fidelity updates lets a frozen text-to-image flow model restore images with high measurement consistency.

  4. Benchmarking GANs, Diffusion Models, and Flow Matching for T1w-to-T2w MRI Translation

    cs.CV 2025-07 conditional novelty 5.0 of 10

    The GAN-based Pix2Pix model outperformed diffusion and flow matching models in a standardized T1w-to-T2w brain MRI translation benchmark on three datasets.

  5. Diffusion Bridge or Flow Matching? A Unifying Framework and Comparative Analysis

    cs.CV 2025-09 reject novelty 4.0 of 10

    A theoretical and empirical comparison claiming diffusion bridges have lower stochastic-optimal-control cost and greater robustness than flow matching when training data are scarce.

  6. Moir\'eXNet: Adaptive Multi-Scale Demoir\'eing with Linear Attention Test-Time Training and Truncated Flow Matching Prior

    cs.CV 2025-06 reject novelty 4.0 of 10

    A RAW-to-sRGB demoireing model built from linear-attention blocks and a truncated flow-matching refinement step reports state-of-the-art PSNR and SSIM on two benchmarks, with internal reporting inconsistencies.

Pith tools