Metraipolis › archive › dc_171c2bddaf64
Diffusion Plug-in Priors for Self-Supervised Ultrasound Video Restoration — arXiv:2611.05206
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.05206
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-04T19:04:55.104Z
- SHA-256 of the archived text
6c59acbeead52ce43e7b96026f30b80793783cfdd7b4ca884fc8c094e0887207- Stable URL of this page
https://metraipolis.com/documento/dc_171c2bddaf64
How to cite
Diffusion Plug-in Priors for Self-Supervised Ultrasound Video Restoration — arXiv:2611.05206 — arXiv (en), https://arxiv.org/abs/2611.05206 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_171c2bddaf64 (Metraipolis archive dc_171c2bddaf64, sha256 6c59acbeead52ce43e7b96026f30b80793783cfdd7b4ca884fc8c094e0887207)
BibTeX
@misc{dc171c2bddaf64,
title = {Diffusion Plug-in Priors for Self-Supervised Ultrasound Video Restoration — arXiv:2611.05206},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.05206},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_171c2bddaf64; sha256 6c59acbeead52ce43e7b96026f30b80793783cfdd7b4ca884fc8c094e0887207},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.05206. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
\textit{Objective:} Ultrasound videos are limited by hardware-constrained spatial resolution and signal-dependent speckle, while paired low- and high-resolution acquisitions for supervised restoration are rarely available. We aim to jointly super-resolve and despeckle ultrasound videos without paired training data or network retraining. \textit{Methods:} We propose UltraDiff, which uses a frozen pre-trained diffusion model (DM) as a plug-in prior and restores each frame by optimizing the latent seed of the DM sampler under a range-constrained maximum a posteriori formulation. We derive a speckle-aware data-fidelity term from a Rayleigh scale-family model and characterize its relative-residual and variance-adaptive weighting properties. We further introduce a stabilized fidelity that is bounded below and strictly convex in log intensity for positive observations in its unclamped form. A total-variation regularizer complements the DM prior, and a temporal seed update warm-starts each frame from the optimized seed of its predecessor. \textit{Results:} On EchoNet-LVH videos with simulated speckle and additive noise, UltraDiff with a natural-image prior improves PSNR by 1.24\,dB over the strongest baseline, and ultrasound-related priors improve it further. On real clinical echocardiography videos, UltraDiff reduces the mean absolute error of zero-shot ejection fraction (EF) prediction from 7.31 to 6.37 EF points relative to DUP, the strongest baseline. \textit{Conclusion:} Combining a speckle-aware fidelity with frozen diffusion priors enables ground-truth-free ultrasound video restoration that benefits downstream measurement. \textit{Significance:} UltraDiff needs neither paired data nor retraining and is not tied to a specific diffusion checkpoint. Code associated with this work will be made publicly available upon acceptance.
Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2611.05206 — 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 2026-11-04T18:39:37.578Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).