“We have ways of making you talk”: Realtime facial puppeting

I don’t know karate, but I know ka-reepy… 

Looks super cool, though the idea of modifying lip syncing makes me envision a car cresting a hill into a desert in which a giant billboard reads “WELCOME TO THE UNCANNY VALLEY.”

Quartz notes,

The project is a collaboration between computer scientists at Stanford University, the Max Planck Institute, and the University of Erlangen-Nuremberg in Germany. The same team produced a similar study last year, but that iteration required data from special 3D cameras. Their new system works with any camera and any recorded video.

I’m also tempted to run the lip sync enhancer in reverse, causing a disconnect between actors & the words they spoke. I’d then dub-aware fill the resulting gaps with awkward coughing & grunting, a la classic chopsocky.

In a related vein, see previous: Apple now owns this facial animation technology.

[YouTube] [Via Kevin McMahon]

2 thoughts on ““We have ways of making you talk”: Realtime facial puppeting

  1. Interesting choice of political actors, I guess a “manipulated ” badge is optional depending on intent,. I can see legitimate uses for altering dialogue and re scripting for tv and film production, a little less happy with black ops usage 🙂

  2. Kind of scary on multiple levels. This kind of technology could be used by many organizations for both good and bad. Imagine creating a short video on Putin saying something that just is not true! Imagine? I guess in the case of Trump or Hillary nothing comes from them thats actually true anyway. Just joking…not. Seriously this is scary stuff but can see how it could be used on multiple fronts.

Leave a Reply

Your email address will not be published.