EUVIMEDEUVIMED entdecken
Crossref

An Introduction to Neural Data Compression

Yibo Yang, Stephan Mandt, Lucas Theis

Foundations and Trends® in Computer Graphics and Vision · 25.04.2023 · 15 (2) · 113-200

DOI: 10.1561/0600000107 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Foundations and Trends® in Computer Graphics and Vision, online erschienen am 25.04.2023. Verfasst von Yibo Yang und 2 weiteren Autor:innen. Die Arbeit wurde bisher 73-mal zitiert (Crossref) und nennt 224 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Neural compression is the application of neural networks and other machine learning methods to data compression. Recent advances in statistical machine learning have opened up new possibilities for data compression, allowing compression algorithms to be learned end-to-end from data using powerful generative models such as normalizing flows, variational autoencoders, diffusion probabilistic models, and generative adversarial networks. This monograph aims to introduce this field of research to a broader machine learning audience by reviewing the necessary background in information theory (e.g., entropy coding, rate-distortion theory) and computer vision (e.g., image quality assessment, perceptual metrics), and providing a curated guide through the essential ideas and methods in the literature thus far.

Zitieren

APA

Yang, Y., Mandt, S., & Theis, L. (2023). An Introduction to Neural Data Compression. Foundations and Trends® in Computer Graphics and Vision, 15(2), 113-200. https://doi.org/10.1561/0600000107

Vancouver

Yang Y, Mandt S, Theis L. An Introduction to Neural Data Compression. Foundations and Trends® in Computer Graphics and Vision. 2023;15(2):113-200. doi:10.1561/0600000107

BibTeX
@article{Yang2023,
  author = {Yang, Yibo and Mandt, Stephan and Theis, Lucas},
  title = {An Introduction to Neural Data Compression},
  journal = {Foundations and Trends® in Computer Graphics and Vision},
  year = {2023},
  volume = {15},
  number = {2},
  pages = {113--200},
  doi = {10.1561/0600000107}
}
Kostenlos starten →