“I am AI : AI-driven Digital Avatar Made Easy” by Liu, Nagano, Seol, Valle, Seo, et al. …

  • ©Ming-yu Liu, Koki Nagano, Yeongho Seol, Rafael Valle, Jaewoo Seo, Ting-Chun Wang, Arun Mallya, Sameh Khamis, Wei Ping, Rohan Badlani, Kevin J. Shih, Bryan Catanzaro, Simon Yuen, and Jan Kautz

Conference:


Entry Number: 103

Title:


    I am AI : AI-driven Digital Avatar Made Easy

Developer(s):


Project Affiliation:


    NVIDIA

Description:


    Won Best In Show

    We introduce a deep learning-based system that allows anyone to synthesize animated digital avatars from audio or text input. We demonstrate our system can generate in real-time lip-synced talking digital avatars from only one picture. We showcase how this technology can enable enhanced video conference experience and accessible avatar creation.

References:


    Ming-yu Liu, Koki Nagano, Yeongho Seol, Rafael Valle, Jaewoo Seo, Ting- Chun Wang, Arun Mallya, Sameh Khamis, Wei Ping, Rohan Badlani, Kevin  J. Shih, Bryan Catanzaro, Simon Yuen, and Jan Kautz. 2021. I am AI : AI- driven Digital Avatar Made Easy. 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/10.1145/3450622.3466785


PDF:



Overview Page:


Type:


E-Tech Type: