EUVIMEDEUVIMED entdecken
Crossref

Rotoscope Automation with Deep Learning

Oscar Estrada Torrejon, Nicholas Peretti, Ricardo Figueroa

SMPTE Motion Imaging Journal · 2020-03 · 129 (2) · 16-26

DOI: 10.5594/jmi.2019.2959967 ↗

Kurz gefasst

Fachartikel in der Zeitschrift SMPTE Motion Imaging Journal, 2020-03. Verfasst von Oscar Estrada Torrejon und 2 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 18 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We present a deep learning-based algorithm that can automatically rotoscope people in a given scene, without any user input. Current approaches to image matting require a significant amount of human input, irrespective of whether it is manually rotoscoped or through a chroma key. This study shows that this algorithm can perform as well as and even surpass the rotoscoping capabilities of the Adobe After Effects’ RotoBrush tool, in a variety of scenes comprising different lighting conditions, movements, and subjects. This makes it suitable for integration within a visual effects (VFX) pipeline.

Zitieren

APA

Torrejon, O. E., Peretti, N., & Figueroa, R. (2020). Rotoscope Automation with Deep Learning. SMPTE Motion Imaging Journal, 129(2), 16-26. https://doi.org/10.5594/jmi.2019.2959967

Vancouver

Torrejon OE, Peretti N, Figueroa R. Rotoscope Automation with Deep Learning. SMPTE Motion Imaging Journal. 2020;129(2):16-26. doi:10.5594/jmi.2019.2959967

BibTeX
@article{Torrejon2020,
  author = {Torrejon, Oscar Estrada and Peretti, Nicholas and Figueroa, Ricardo},
  title = {Rotoscope Automation with Deep Learning},
  journal = {SMPTE Motion Imaging Journal},
  year = {2020},
  volume = {129},
  number = {2},
  pages = {16--26},
  doi = {10.5594/jmi.2019.2959967}
}
Kostenlos starten →