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

TL;DR

This paper introduces PnP-Flow, a novel image restoration method combining plug-and-play denoisers with flow matching models, achieving state-of-the-art results efficiently across various inverse imaging tasks.

Contribution

It proposes a new algorithm that integrates flow matching models into the PnP framework, enabling efficient and effective image restoration.

Findings

Superior performance on denoising, super-resolution, deblurring, and inpainting.

Computationally efficient and memory-friendly approach.

Outperforms existing PnP and flow matching methods.

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.