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.

翻译：本文提出了一种用于求解成像逆问题的算法——即插即用（PnP）流匹配方法。PnP方法通过将预训练的降噪器（通常为深度神经网络）集成到优化框架中，充分发挥其优势。尽管PnP方法在各种成像逆问题上取得了最先进的性能，但在修复等更具生成性的任务中存在固有局限。另一方面，流匹配等生成模型虽在图像采样方面取得突破，却缺乏用于图像复原的高效调用机制。我们提出将PnP框架与流匹配（FM）相结合，利用预训练的FM模型构建时变降噪器。该算法交替执行数据保真项的梯度下降、学习到的FM路径重投影以及降噪处理。值得注意的是，本方法通过避免常微分方程的反向传播和迹计算，实现了计算高效与内存友好的特性。我们在去噪、超分辨率、去模糊和修复任务上评估了算法性能，结果表明其优于现有PnP算法及基于流匹配的先进方法。