{"ID":2888032,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.00721","arxiv_id":"2508.00721","title":"FMPlug: Plug-In Foundation Flow-Matching Priors for Inverse Problems","abstract":"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.","short_abstract":"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 o...","url_abs":"https://arxiv.org/abs/2508.00721","url_pdf":"https://arxiv.org/pdf/2508.00721v2","authors":"[\"Yuxiang Wan\",\"Ryan Devera\",\"Wenjie Zhang\",\"Ju Sun\"]","published":"2025-08-01T15:40:37Z","proceeding":"eess.IV","tasks":"[\"eess.IV\",\"cs.CV\",\"cs.LG\",\"eess.SP\"]","methods":"[]","has_code":false}