Metraipolis › archive › dc_3f475f7e027b

PEEL-DDPM: Physics-Enabled Evidential Learning for the Denoising Diffusion Probabilistic Model — arXiv:2609.31742

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.31742
License (as archived)
CC0-1.0
Archived
2026-10-07T23:50:34.127Z
SHA-256 of the archived text
9bfdd33af730ec29f1de4fc40254aae1128087720e551c39edbf62ed4e218c55
Stable URL of this page
https://metraipolis.com/documento/dc_3f475f7e027b

How to cite

PEEL-DDPM: Physics-Enabled Evidential Learning for the Denoising Diffusion Probabilistic Model — arXiv:2609.31742 — arXiv (en), https://arxiv.org/abs/2609.31742 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3f475f7e027b (Metraipolis archive dc_3f475f7e027b, sha256 9bfdd33af730ec29f1de4fc40254aae1128087720e551c39edbf62ed4e218c55)
BibTeX
@misc{dc3f475f7e027b,
  title = {PEEL-DDPM: Physics-Enabled Evidential Learning for the Denoising Diffusion Probabilistic Model — arXiv:2609.31742},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.31742},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3f475f7e027b; sha256 9bfdd33af730ec29f1de4fc40254aae1128087720e551c39edbf62ed4e218c55},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.31742. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Normal-inverse-gamma (NIG) regression is not identifiable from its marginal Student-t likelihood: three combinations of four NIG parameters are determined, leaving one degree of freedom. We introduce PEEL-DDPM, a physics-enabled evidential learning framework for denoising diffusion probabilistic models. A measurement-conditioned DDPM is first trained with epsilon-MSE and then frozen. Its complete reverse trajectory produces a reconstruction, whose residual from the known training object is modeled by a final-image evidential network. The network learns only the identifiable Student-t coordinates, while repeated scanner-noise realizations and repeated diffusion trajectories provide a nested Monte Carlo estimate of final-image aleatoric variance, separated into scanner-induced and sampler-induced components. This measured variance resolves the remaining NIG ambiguity and yields a decomposition of predictive uncertainty into measurement, diffusion, and epistemic terms. The method uses sequential training without a cross-loss weighting coefficient. In a feasibility study on eight held-out objects, empirical central-interval coverages were 49.3%, 80.3%, 90.1%, and 95.6% for nominal 50%, 80%, 90%, and 95% intervals. The mean squared residual was 0.967 times the mean predicted variance, and a single-image aleatoric head achieved pooled Spearman correlation 0.785 against an independent nested reference. Across five dose levels, scanner-induced variance showed a log-log dose slope of -1.15, whereas sampler-induced variance remained nearly dose independent with slope -0.01. These results support PEEL-DDPM as a practical route to identifiable and physically interpretable uncertainty quantification in diffusion-based image reconstruction.

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/2609.31742 — 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 2026-10-07T23:29:26.911Z 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).