Metraipolis › archive › dc_85201801f51f

A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors — arXiv:2608.15144

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.15144
License (as archived)
CC0-1.0
Archived
2026-10-18T18:01:57.891Z
SHA-256 of the archived text
a534cc099431856aa9c7d1f50b54ac005e469b14a47a850fd0b4c7068c234280
Stable URL of this page
https://metraipolis.com/documento/dc_85201801f51f

How to cite

A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors — arXiv:2608.15144 — arXiv (en), https://arxiv.org/abs/2608.15144 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_85201801f51f (Metraipolis archive dc_85201801f51f, sha256 a534cc099431856aa9c7d1f50b54ac005e469b14a47a850fd0b4c7068c234280)
BibTeX
@misc{dc85201801f51f,
  title = {A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors — arXiv:2608.15144},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.15144},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_85201801f51f; sha256 a534cc099431856aa9c7d1f50b54ac005e469b14a47a850fd0b4c7068c234280},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.15144. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Pretrained diffusion models represent image distributions through a continuum of progressively smoothed distributions. This multiscale structure organizes generation from global structure to fine detail and supports high-quality, diverse samples. We exploit the same multiscale diffusion prior for linear imaging inverse problems. Rather than using the pretrained model only as a denoiser in an outer iteration, we define a surrogate likelihood whose center is aligned with the clean-image coordinate and whose covariance accounts for residual diffusion uncertainty. This construction defines an explicit surrogate posterior path, from which we derive continuous posterior dynamics. A tunable Langevin component supports target tracking and allows the amount of posterior exploration to be adapted to the application. We prove endpoint consistency and a finite-horizon tracking bound and, in the exact-score setting, first-order weak accuracy. For computation, we derive the Posterior-Dynamics Implicit--Explicit sampler (PD-IMEX), a stable method using one score evaluation per diffusion scale and an implicit data-consistency update. Experiments on deblurring, super-resolution, and inpainting show strong reconstruction quality at 100 score evaluations, coarse-grid stability, and controllable fidelity--diversity behavior.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI).
Categorie arXiv: Machine Learning (stat.ML) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.15144 — 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 2026-10-18T16:29:13.989Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).