Metraipolis › archive › dc_ccc2019621ab

SNaP: One-Step Posterior Sampling for Noisy Inverse Problems — arXiv:2609.34071

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.34071
License (as archived)
CC0-1.0
Archived
2026-10-07T23:51:51.140Z
SHA-256 of the archived text
9eddf3b69e6fe8d1f4c775460faa97bd9d58f36ad21979db78c9f2507a2c634d
Stable URL of this page
https://metraipolis.com/documento/dc_ccc2019621ab

How to cite

SNaP: One-Step Posterior Sampling for Noisy Inverse Problems — arXiv:2609.34071 — arXiv (en), https://arxiv.org/abs/2609.34071 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ccc2019621ab (Metraipolis archive dc_ccc2019621ab, sha256 9eddf3b69e6fe8d1f4c775460faa97bd9d58f36ad21979db78c9f2507a2c634d)
BibTeX
@misc{dcccc2019621ab,
  title = {SNaP: One-Step Posterior Sampling for Noisy Inverse Problems — arXiv:2609.34071},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.34071},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ccc2019621ab; sha256 9eddf3b69e6fe8d1f4c775460faa97bd9d58f36ad21979db78c9f2507a2c634d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34071. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Diffusion and flow-matching models can produce high-quality posterior samples for inverse problems, but typically require tens to thousands of network evaluations per draw. MeanFlow enables one-step generation, yet applying it to inverse problems leaves no intermediate steps at which to enforce measurement consistency. We introduce SNaP, a one-step MeanFlow posterior sampler for linear inverse problems with Gaussian noise. Its central innovation is a measurement-adapted source: a Gaussian distribution whose mean and anisotropic covariance are determined by the measurement operator, observation, and noise level. The source anchors well-measured directions while preserving variation where the measurements are weak or uninformative. We show that the exact conditional flow transports this source to the true posterior. Across natural-image restoration and multi-coil MRI, SNaP produces diverse, high-quality samples with one network evaluation per draw, 30 to 2250 $\times$ faster than iterative samplers.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.34071 — 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 2026-10-07T23:29:27.283Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).