How can you be anybody in Zoomspace? Very recent developments in deep-learning, allow creating synthetic media of unprecedented quality and ease. The first-order-motion-model can do facial reenactment in real-time, provided with only a single image of your desired avatar. This came not a moment too soon, as Human communication was forced to move online due to the Coronavirus pandemic. Can this be an opportunity to fulfill the long promised cybernetic utopia, where we could shed our physical shells and become however we wish to be? And how does this pertain to issues of privacy, identity and trust?
I will review the contemporary technologies and show how I use them in my artistic and activist practices. This is a hands-on participatory and creative tutorial, where you will create deep-fake videos using your own materials, and play with various options of becoming an online avatar. No prior knowledge needed. I will also introduce and demo the first available purely online solution for live real-time avatars from the webcam, and show how I try to make these state-of-the-art technologies accessible to a wide audience using Google Colab. repo: github.com/eyaler/avatars4all

The tutorial will take place online, as part of the International Conference on Computational Creativity, on September 14-18, 2021.

Schedule

September 14, 2021

11:00 to 14:30 Mexico time

16:00 to 19:30 UTC

Zoom link here: https://underline.io/events/178/sessions?eventSessionId=7057

Organizers

Contact the organizers please send an email to eyalgruss@gmail.com.