标题： FMPlug：逆问题的插件基础流匹配先验 显示英文标题

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

摘要： 我们提出FMPlug，一种新颖的插件框架，用于增强基础流匹配（FM）先验，以解决不适定逆问题。 与依赖领域特定或未训练先验的传统方法不同，FMPlug巧妙地利用了两个简单但强大的见解：观察到的和期望的物体之间的相似性以及生成流的高斯性。 通过引入时间自适应预热策略和精确的高斯正则化，FMPlug释放了领域无关基础模型的真正潜力。 我们的方法在图像超分辨率和高斯模糊去卷积任务中，显著优于使用基础FM先验的最先进方法。 显示英文摘要

摘要： 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.