Mar 21, 2016 | By Tess

In an age of skepticism and of image manipulation through such accessible softwares as Photoshop, news clips and videos have remained somewhat more believable than, say, a magazine cover. Perhaps not for long, however, as a team of university researchers have developed a new video technology that is capable of transferring one person’s facial expressions and movements onto another person’s face in real time, using only a commodity webcam as a sort of 3D facial scanner.

The technology, called Face2Face, was developed through a joint effort by the University of Erlangen-Nuremberg, the Max Planck Institute for Informatics, and Stanford University, and though it is still in its early stages, the results of the face capture and reenactment are truly impressive, and admittedly, a bit unsettling.

In a video put out by the team of researchers that demonstrates how the technology works, we see the facial movements of their test subject’s being reenacted in real time by such politicians as Barack Obama, George W. Bush, Vladmir Putin, and Donald Trump. As the test subject, who is simply placed in front of an off-the-shelf camera, smiles, winces, or opens their mouth wide, so does the politician featured in the youtube video selected by the researchers. The implications of such a technology could mean something as simple as turning a frown into a smile, but as it advances, could eventually mean putting words into someone else’s mouth, a reason to be more wary of youtube clips that pop up on your social media newsfeeds.

The Face2Face technology works by using RGB input, which allows for the facial movements of the test subject, captured by any commodity webcam, to be translated in real time to a monocular video sequence, such as a youtube clip. The study explains, “At run time, we track facial expressions of both source and target video using a dense photometric consistency measure. Reenactment is then achieved by fast and efficient deformation transfer between source and target. The mouth interior that best matches the re-targeted expression is retrieved from the target sequence and warped to produce an accurate fit. Finally, we convincingly re-render the synthesized target face on top of the corresponding video stream such that it seamlessly blends with the real-world illumination.”

While the rendered videos of George W. Bush and Donald Trump look convincing enough, we hope that when a video edited through the new Face2Face technology inevitably pops up on social media, the still uncanny quality of the videos will tip us off to the trick. Of course, just like Photoshopped photos, this new video technology will help to remind us to be critical and always wary of the information we ingest from the internet.



Posted in 3D Scanning



Maybe you also like:


Leave a comment:

Your Name:


Subscribe us to Feeds twitter facebook   

About provides the latest news about 3D printing technology and 3D printers. We are now five years old and have around 1.5 million unique visitors per month.

News Archive