Those who are in the film industry know how much effort the actors and directors have to put just to capture the right emotion at the right time. Some directors are even so famous for demanding that scenes be shot and re-shot repeatedly until they get the perfect emotion from the actors. It’s not only time consuming, but also costs a lot of money. What if the directors could fine-tune performances in post-production, rather than on the film set? Now they can. Here comes FaceDirector, a new system developed by Disney Research and the University of Surrey.
With FaceDirector, the director will be able to seamlessly blend facial images from a couple of videos to create the exact facial expression they want. They don’t even need any specialized tools like 3D camera. This trick even works with the footage taken by a regular 2D camera. By analyzing both the actor’s face and audio hints to identify the frames that correspond with each other, it creates the perfect emotion.
“It’s not unheard of for a director to re-shoot a crucial scene dozens of times, even 100 or more time, until satisfied,” said Markus Gross, vice president of research at Disney Research. “That not only takes a lot of time- it also can be quite expensive. Now our research team has shown that a director can exert control over an actor’s performance after the shoot with just a few takes, saving both time and money.”
If it’s still difficult for you to visualize how this software works, make sure you watch the following video.