Pushing Deepfakes to the Limit - Fake video calls with AI
AI/Machine Learning
• October 2022
Pushing Deepfakes to the Limit - Fake video calls with AI
About
Pushing Deepfakes to the Limit - Fake video calls with AI
About
"Today's real-time Deepfake technology makes it possible to create indistinguishable doppelgängers of a person and let them participate in video calls. Since 2019, the TNG Innovation Hacking Team has intensively researched and continuously developed the AI around real-time Deepfakes. The final result and the individual steps towards photorealism will be presented in this talk.
In this talk we will show the different evolutionary steps of the Deepfake technology. Several live demos will shed light on individual components of the software."
Language
English
Level
Intermediate
Length
38 minutes
Type
About the speakers
About the speakers
Martin Förtsch
Principal Consultant •
TNG Technology Consulting GmbH
Martin Förtsch studied computer science and is working as a software consultant for Munich based IT consulting company TNG Technology Consulting GmbH. Occupational his focus areas are Agile Development with Java, search engine technologies and databases. As an Intel Software Innovator he is strongly involved in the development of software for gesture control with 3D-cameras like Intel RealSense and built an Augmented Reality wearable device based on this technology.
Jonas Mayer
Senior Consultant •
TNG Technology Consulting GmbH
Jonas Mayer works in the Innovation Hacking Team of TNG Technology Consulting where his main focus lies on creating innovative showcases and prototypes in both soft- and hardware. Since 2018 he's been working on numerous projects ranging from real-time deepfakes, over mixed reality art experiences, all the way to autonomous miniature drones.
Prior to joining TNG, Jonas studied Informatics: Games Engineering at TU Munich. Apart from the obvious game projects throughout the course of his studies, he focused mainly on artificial intelligence and high performance computing.
Details
Language
English
Level
Intermediate
Length
38 minutes
Type
Related tags
Related tags