EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Generalised Diffusion Probabilistic Scale-Spaces

Pascal Peter

Journal of Mathematical Imaging and Vision · 2024-08 · 66 (4) · 639-656

DOI: 10.1007/s10851-024-01202-0 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Mathematical Imaging and Vision, online erschienen am 17.06.2024. Verfasst von Pascal Peter. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 78 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Universität des Saarlandes.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Diffusion probabilistic models excel at sampling new images from learned distributions. Originally motivated by drift-diffusion concepts from physics, they apply image perturbations such as noise and blur in a forward process that results in a tractable probability distribution. A corresponding learned reverse process generates images and can be conditioned on side information, which leads to a wide variety of practical applications. Most of the research focus currently lies on practice-oriented extensions. In contrast, the theoretical background remains largely unexplored, in particular the relations to drift-diffusion. In order to shed light on these connections to classical image filtering, we propose a generalised scale-space theory for diffusion probabilistic models. Moreover, we show conceptual and empirical connections to diffusion and osmosis filters.

Förderung

  • Universität des Saarlandes

Zitieren

APA

Peter, P. (2024). Generalised Diffusion Probabilistic Scale-Spaces. Journal of Mathematical Imaging and Vision, 66(4), 639-656. https://doi.org/10.1007/s10851-024-01202-0

Vancouver

Peter P. Generalised Diffusion Probabilistic Scale-Spaces. Journal of Mathematical Imaging and Vision. 2024;66(4):639-656. doi:10.1007/s10851-024-01202-0

BibTeX
@article{Peter2024,
  author = {Peter, Pascal},
  title = {Generalised Diffusion Probabilistic Scale-Spaces},
  journal = {Journal of Mathematical Imaging and Vision},
  year = {2024},
  volume = {66},
  number = {4},
  pages = {639--656},
  doi = {10.1007/s10851-024-01202-0}
}
Kostenlos starten →