“Normalized Avatar Digitization for Communication in VR” by Li, Wang, Wei, Goldwhite, Hu, et al. …
Conference:
Type(s):
E-Tech Type(s):
- Virtual Reality
Entry Number: 122
Title:
- Normalized Avatar Digitization for Communication in VR
Developer(s):
Description:
We introduce a highly robust GAN-based framework for digitizing a normalized 3D avatar of a person from a single unconstrained photo. We demonstrate a multi-user VR chatting system using Oculus Quest 2 where performances are driven by the headset and controllers and facial animation through speech-to-face synthesis.
References:
Hao Li, Zejian Wang, Lingyu Wei, McLean Goldwhite, Liwen Hu, Raymond Mosco, Han-Wei Kung, Huiwen Luo, and Koki Nagano. 2021. Normalized Avatar Digitization for Communication in VR. In Special Interest Group on Computer Graphics and Interactive Techniques Conference Real-Time Live! (SIGGRAPH ’21 Real-Time Live!), August 09-13, 2021. ACM, New York, NY, USA, 1 page. https://doi.org/10.1145/3450622.3466792
PDF:
Submit a story:
If you would like to submit a story about this experience or presentation, please contact us: historyarchives@siggraph.org
