EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Artificial-Intelligence-Generated Content with Diffusion Models: A Literature Review

Xiaolong Wang, Zhijian He, Xiaojiang Peng

Mathematics · 25.03.2024 · 12 (7) · 977

DOI: 10.3390/math12070977 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Mathematics, online erschienen am 25.03.2024. Verfasst von Xiaolong Wang und 2 weiteren Autor:innen. Die Arbeit wurde bisher 47-mal zitiert (Crossref) und nennt 84 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Stable Support Projects for Shenzhen Higher Education Institutions, Natural Science Foundation of Top Talent of SZTU.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Diffusion models have swiftly taken the lead in generative modeling, establishing unprecedented standards for producing high-quality, varied outputs. Unlike Generative Adversarial Networks (GANs)—once considered the gold standard in this realm—diffusion models bring several unique benefits to the table. They are renowned for generating outputs that more accurately reflect the complexity of real-world data, showcase a wider array of diversity, and are based on a training approach that is comparatively more straightforward and stable. This survey aims to offer an exhaustive overview of both the theoretical underpinnings and practical achievements of diffusion models. We explore and outline three core approaches to diffusion modeling: denoising diffusion probabilistic models, score-based generative models, and stochastic differential equations. Subsequently, we delineate the algorithmic enhancements of diffusion models across several pivotal areas. A notable aspect of this review is an in-depth analysis of leading generative models, examining how diffusion models relate to and evolve from previous generative methodologies, offering critical insights into their synergy. A comparative analysis of the merits and limitations of different generative models is a vital component of our discussion. Moreover, we highlight the applications of diffusion models across computer vision, multi-modal generation, and beyond, culminating in significant conclusions and suggesting promising avenues for future investigation.

Förderung

  • National Natural Science Foundation of China
  • Stable Support Projects for Shenzhen Higher Education Institutions
  • Natural Science Foundation of Top Talent of SZTU

Zitieren

APA

Wang, X., He, Z., & Peng, X. (2024). Artificial-Intelligence-Generated Content with Diffusion Models: A Literature Review. Mathematics, 12(7), 977. https://doi.org/10.3390/math12070977

Vancouver

Wang X, He Z, Peng X. Artificial-Intelligence-Generated Content with Diffusion Models: A Literature Review. Mathematics. 2024;12(7):977. doi:10.3390/math12070977

BibTeX
@article{Wang2024,
  author = {Wang, Xiaolong and He, Zhijian and Peng, Xiaojiang},
  title = {Artificial-Intelligence-Generated Content with Diffusion Models: A Literature Review},
  journal = {Mathematics},
  year = {2024},
  volume = {12},
  number = {7},
  pages = {977},
  doi = {10.3390/math12070977}
}
Kostenlos starten →