“AI-Synthesized Avatars: From Real-Time Deepfakes to Photoreal AI Virtual Assistant” by Wang, Nagano, Li, Hu, Goldwhite, et al. …
Conference:
Experience Type(s):
E-Tech Type(s):
Title:
- AI-Synthesized Avatars: From Real-Time Deepfakes to Photoreal AI Virtual Assistant
Developer(s):
- Koki Nagano
- Hao Li
- Liwen Hu
- Lain Goldwhite
- Han-Wei Kung
- Aviral Agarwal
- Yenchun Chen
- Qingguo Xu
- Jaewoo Seo
Project Affiliation:
- Pinscreen
Description:
We introduce a real-time deep learning-based facial synthesis technology for photoreal AI-avatars, and demonstrate two novel applications. We showcase the first zero-shot real-time deepfake system allowing anyone to swap their faces with another subject. Then, we demonstrate how this technology can enable an AI- based photoreal virtual assistant.
ACM Digital Library Publication:
Overview Page:
Submit a story:
If you would like to submit a story about this experience or presentation, please contact us: historyarchives@siggraph.org
