Rotoscope Automation with Deep Learning
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.
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}
}
EUVIMED