In a paper presented at the 2015 SIGGRAPH Asia conference, researchers from the University of Erlangen-Nuremberg, the Max Planck Institute for Informatics, and Stanford University demonstrated the ability to transfer facial expressions from one person in a video to another in real time. In other words, the technology would allow my smile to appear on a CGI representation of your face, at what the researchers call “previously unseen visual realism.”
A sensor analyzes faces in terms of their geometry and the reflectance of different regions of the skin. Essentially, it creates virtual models of the faces of both participants and the lighting in the video, so that the facial expression of one person can be pasted over the face of another. The technology computes the difference between the first person’s expression and the target’s face, and renders them together. The goal is to only manipulate the parts of the face necessary for that particular facial expression, rather than changing the target’s entire face.
via Mental Floss
Image: MATTHIAS NIESSNER VIA STANFORD UNIVERSITY
