paper-with-me

Papers

Saving Foundation Flow-Matching Priors for Inverse Problems

2025-11-20 · Yuxiang Wan, Ryan Devera, Wenjie Zhang, Ju Sun arxiv

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 introduce FMPlug, a plug-in framework that redefines how foundation FMs are used in IPs. FMPlug combines an instance-guided, time-dependent warm-start strategy with sharp Gaussianity regularization, adding problem-specific guidance while preserving the Gaussian structures. For evaluation, we consider both simple image restoration tasks and scientific IPs with a few similar samples -- where the prohibitive cost of data collection and model training hinders the development of domain-specific generative models. Our superior experimental results confirm the effectiveness of FMPlug. Overall, FMPlug paves the way for making foundation FM models practical, reusable priors for IPs, especially scientific ones with few similar samples. More details are available at https://sun-umn.github.io/xm-plug/ .

📄 PDF Abstract BibTeX arXiv:2511.16520

Code (0)

등록된 구현이 없습니다.

Tasks

Image Restoration

Similar Papers 제목 키워드 기반

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

2025-08-01 · Yuxiang Wan, Ryan Devera, Wenjie Zhang, Ju Sun arxiv

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, FMPl…

Image Super-Resolution

Latent Refinement via Flow Matching for Training-free Linear Inverse Problem Solving

2025-11-08 · Hossein Askari, Yadan Luo, Hongfu Sun, Fred Roosta arxiv

Recent advances in inverse problem solving have increasingly adopted flow priors over diffusion models due to their ability to construct straight probability paths from noise to data, thereby enhancing efficiency in both…

Flow Priors for Linear Inverse Problems via Iterative Corrupted Trajectory Matching

2024-05-29 · Yasi Zhang, Peiyu Yu, Yaxuan Zhu, Yingshan Chang 외

Generative models based on flow matching have attracted significant attention for their simplicity and superior performance in high-resolution image synthesis. By leveraging the instantaneous change-of-variables formula,…

compressed sensingDeblurringImage GenerationSuper-Resolution

Physics-Guided Flow Matching for CT Image Reconstruction

2026-08-28 · Davide Evangelista arxiv

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 Augmentation

D-Flow SGLD: Source-Space Posterior Sampling for Scientific Inverse Problems with Flow Matching

2026-02-25 · Meet Hemant Parikh, Yaqin Chen, Jian-Xun Wang arxiv

Data assimilation and scientific inverse problems require reconstructing high-dimensional physical states from sparse and noisy observations, ideally with uncertainty-aware posterior samples that remain faithful to learn…