FMPlug: Plug-In Foundation Flow-Matching Priors for Inverse Problems
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Image Super-ResolutionSimilar Papers 제목 키워드 기반
Saving Foundation Flow-Matching Priors for Inverse Problems
Foundation flow-matching (FM) models promise universal priors for solving inverse problems (IPs); yet today, they trail behind domain-specific and even untrained priors. \emph{How can we unlock their potential?} We intro…
Image RestorationPhysics-Guided Flow Matching for CT Image Reconstruction
Deep generative models have recently emerged as powerful priors for solving ill-posed inverse problems in CT, with diffusion-based approaches achieving state-of-the-art reconstruction performance. However, diffusion mode…
Computational EfficiencyImage ReconstructionData AugmentationRFMSR: Residual Flow Matching for Image Super-Resolution
Image super-resolution (ISR) has witnessed remarkable progress with diffusion models and flow matching. The dominant text-to-image (T2I) based approaches leverage large-scale foundation models as generative priors, achie…
Image Super-ResolutionRethinking Dense Optical Flow without Test-Time Scaling
Recent progress in dense optical flow has been driven by increasingly complex architectures and multi-step refinement for test-time scaling. While these approaches achieve strong benchmark performance, they also require …
Text-to-Image Rectified Flow as Plug-and-Play Priors
Large-scale diffusion models have achieved remarkable performance in generative tasks. Beyond their initial training applications, these models have proven their ability to function as versatile plug-and-play priors. For…
3D GenerationText to 3D