用流匹配先验提升图像逆问题求解效果
FMPlug: Plug-In Foundation Flow-Matching Priors for Inverse Problems
- 利用观测与目标相似性及生成流高斯性设计新框架
- 在超分辨率和高斯去模糊任务上超越现有方法
- 适合需要通用先验的图像重建场景
我们提出FMPlug，一种新型插件式框架，用于增强基础流匹配（FM）先验以解决病态逆问题。不同于依赖领域特定或未训练先验的传统方法，FMPlug巧妙利用两个简单但强大的洞察：观测数据与目标对象间的相似性，以及生成流的高斯特性。通过引入时间自适应预热策略和强高斯正则化，FMPlug充分释放了无领域限制的基础模型潜力。该方法在图像超分辨率和高斯去模糊任务上显著优于使用基础流匹配先验的现有最先进方法。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。