Pre-recorded videos can be edited in real-time via facial capture and re-enactment technology, thanks to software developed by researchers from Stanford University in the US and the University of Erlangen-Nuremberg and Max Planck Institute for Informatics in Germany.
The purpose of their study, which will be published in Computer Vision and Pattern Recognition, was to demonstrate the capabilities of modern computer vision and graphics technology.
In the video below you can see how facial expressions in a target video are animated to match the expressions of a source actor in real-time. The software re-renders the manipulated output video in a photo-realistic fashion.
The effect of seamlessly blending real-world facial movements and those within a video is impressive, if not a little terrifying.
Originally published by Cosmos as Video: real-time facial manipulation technology
Cosmos is a quarterly science magazine. We aim to inspire curiosity in ‘The Science of Everything’ and make the world of science accessible to everyone.
Read science facts, not fiction...
There’s never been a more important time to explain the facts, cherish evidence-based knowledge and to showcase the latest scientific, technological and engineering breakthroughs. Cosmos is published by The Royal Institution of Australia, a charity dedicated to connecting people with the world of science. Financial contributions, however big or small, help us provide access to trusted science information at a time when the world needs it most. Please support us by making a donation or purchasing a subscription today.