Mapping of Facial Action Units to Virtual Avatar Blend Shape Movement
dc.contributor.author | Wolff, Tony | en_US |
dc.contributor.author | Dollack, Felix | en_US |
dc.contributor.author | Perusquia-Hernandez, Monica | en_US |
dc.contributor.author | Uchiyama, Hideaki | en_US |
dc.contributor.author | Kiyokawa, Kiyoshi | en_US |
dc.contributor.editor | Tanabe, Takeshi | en_US |
dc.contributor.editor | Yem, Vibol | en_US |
dc.date.accessioned | 2024-11-29T06:38:12Z | |
dc.date.available | 2024-11-29T06:38:12Z | |
dc.date.issued | 2024 | |
dc.description.abstract | Action Units and blend shapes are two frameworks to describe facial movement. However, mappings between the two frameworks are underinvestigated. We present an automated mapping technique using machine learning. Our model infers ARKitcompatible blend shape weights from action unit intensities extracted with OpenFace. We use a GRU architecture to retain time-dependent information leveraging the particularities of Recurrent Neural Networks while still permitting fast, real-time inference. Our generalized model yields an activation precision of 90% and an activation recall of 85%. | en_US |
dc.description.sectionheaders | Posters | |
dc.description.seriesinformation | ICAT-EGVE 2024 - International Conference on Artificial Reality and Telexistence and Eurographics Symposium on Virtual Environments - Posters and Demos | |
dc.identifier.doi | 10.2312/egve.20241392 | |
dc.identifier.isbn | 978-3-03868-246-2 | |
dc.identifier.issn | 1727-530X | |
dc.identifier.pages | 2 pages | |
dc.identifier.uri | https://doi.org/10.2312/egve.20241392 | |
dc.identifier.uri | https://diglib.eg.org/handle/10.2312/egve20241392 | |
dc.publisher | The Eurographics Association | en_US |
dc.rights | Attribution 4.0 International License | |
dc.rights.uri | https://creativecommons.org/licenses/by/4.0/ | |
dc.subject | CCS Concepts: Human-centered computing → Virtual reality; Computing methodologies → Machine learning algorithms | |
dc.subject | Human centered computing → Virtual reality | |
dc.subject | Computing methodologies → Machine learning algorithms | |
dc.title | Mapping of Facial Action Units to Virtual Avatar Blend Shape Movement | en_US |
Files
Original bundle
1 - 1 of 1