Metraipolis › archive › dc_ebdd2fecdf42

FlowSGS: Improving Flow Matching Priors for Inverse Imaging with Stochastic Interpolants — arXiv:2609.20769

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.20769
License (as archived): CC0-1.0
Archived: 2026-10-10T05:08:07.669Z
SHA-256 of the archived text: afa3faa731eb0ae9def5694f402e66691d7bf9cfaa935642dc62796ed5b75eee
Stable URL of this page: https://metraipolis.com/documento/dc_ebdd2fecdf42

How to cite

FlowSGS: Improving Flow Matching Priors for Inverse Imaging with Stochastic Interpolants — arXiv:2609.20769 — arXiv (en), https://arxiv.org/abs/2609.20769 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ebdd2fecdf42 (Metraipolis archive dc_ebdd2fecdf42, sha256 afa3faa731eb0ae9def5694f402e66691d7bf9cfaa935642dc62796ed5b75eee)

BibTeX

@misc{dcebdd2fecdf42,
  title = {FlowSGS: Improving Flow Matching Priors for Inverse Imaging with Stochastic Interpolants — arXiv:2609.20769},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.20769},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ebdd2fecdf42; sha256 afa3faa731eb0ae9def5694f402e66691d7bf9cfaa935642dc62796ed5b75eee},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.20769. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Flow matching has emerged as the state-of-the-art generative model and has been used for plug-and-play (PnP) priors to solve inverse problems in computational imaging. However, existing flow-based inverse solvers assume linear forward models and/or make simplifying approximations in posterior sampling. To circumvent these problems, we introduce FlowSGS, a flow-based posterior sampling method using Split Gibbs Sampling (SGS) to decompose the posterior into a likelihood step and a prior step. Specifically, we sample from the likelihood step using Langevin dynamics and leverage the Stochastic Interpolants (SI) framework to integrate a pretrained flow model into the prior step. We provide a form for the prior step that uses SI's reverse-time SDE, and show connections to previous PnP methods. Moreover, with the aid of the flow prior's straight probability paths and a novel timestep correction technique for the reverse-time SDE, FlowSGS requires fewer network evaluations in its prior step than plug-and-play diffusion samplers. Our experiments show state-of-the-art performance on a range of inverse problems. For the first time, we provide an experiment on a nonlinear inverse problem (Fourier phase retrieval) for flow-based inverse solvers.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-18 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.20769 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-10T04:26:09.630Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).