Skip to main content

Disney Research develops method to capture 3D facial performances with a single camera

disney research single camera facial performance capture
Disney Research
Capturing an actor’s facial performance in a three-dimensional environment is key to believable animations in movies and video games. The process of accurately modeling a performer’s face — and their full range of expressions — is no easy task, however. But with a new method developed by Disney Research, it’s about to become much simpler.

Unlike traditional facial-performance-capture techniques, which rely on multiple cameras to read depth information, this new method uses only a single camera. And no, it doesn’t require a light-field camera or any other non-traditional imaging device. In fact, the researchers even demonstrated it using both a GoPro and an iPhone, according to a press release first seen on Phys.org.

Related Videos

Single-camera facial-performance capture isn’t completely new, but existing methods require a complex computer model of an actor’s face to be developed ahead of time. That model has to be built with many different expressions programmed into it, otherwise the capture process will generate too many anomalies.

With Disney Research’s new method, information about bone structure and skin thickness is taken into account, which provides an “anatomically constrained” model, thereby keeping the range of available animations limited to what’s physically possible, without the need for as many pre-recorded expressions. The effectiveness of the method was tested by capturing an actor’s face being deformed by a jet of compressed air, something that simply wouldn’t be possible with other single-camera solutions.

Smaller, less complex hardware should make facial performance capture more accessible and easier to do. A single-camera system also allows actors increased freedom of movement during their performances. While typically there exists an inverse relationship between simplicity and capture quality, Disney researchers say their new method bucks the trend.

“No hardware setup could be simpler than our new one-camera method, yet we’ve shown that it can obtain results that rival, if not exceed, more traditional methods,” Markus Gross, vice president of Disney Research, said in the press release.

The project will be presented on July 24 at the ACM International Conference on Computer Graphics & Interactive Techniques (SIGGRAPH) in California.

Editors' Recommendations

DJI Mini 3 Pro unboxing video drops just ahead of launch
DJI's new Mini 3 Pro drone, according to a leaked image.

DJI is expected to unveil the third iteration of its plucky Mini drone on Tuesday, May 10, but a video has already dropped showing in great detail what appears to be the new flying machine and its controller.

The three-minute unboxing video (below) comes courtesy of YouTuber Darren McHardy (via DroneDJ), who recently received the footage from DJI observer Jasper Ellens.

Read more
James Webb Space Telescope fully aligned and capturing crisp images
Engineering images of sharply focused stars in the field of view of each instrument demonstrate that the telescope is fully aligned and in focus.

Since the launch of the James Webb Space Telescope in December last year, engineers have been working to deploy the telescope's hardware, then align both its mirrors and its instruments. Now, that months-long process is complete, and the telescope is confirmed to be fully aligned. NASA and the European Space Agency have shared an image showing the sharpness check of all of Webb's instruments, showing that they are all crisp and properly focused.

"Engineering images of sharply focused stars in the field of view of each instrument demonstrate that the telescope is fully aligned and in focus," the European Space Agency writes. "For this test, Webb pointed at part of the Large Magellanic Cloud, a small satellite galaxy of the Milky Way, providing a dense field of hundreds of thousands of stars across all the observatory’s sensors. The sizes and positions of the images shown here depict the relative arrangement of each of Webb’s instruments in the telescope’s focal plane, each pointing at a slightly offset part of the sky relative to one another."

Read more
NASA’s asteroid investigator Lucy tests out its four cameras
The faintest visible stars in this raw L’LORRI image are roughly 17th magnitude, 50,000 times fainter than the unaided human eye can see. Image brightness levels have been adjusted to enhance visibility of faint stars. The exposure time was 10 seconds. Keen observers will notice that the stars are slightly elongated in this relatively unprocessed image; the Lucy team has techniques to mitigate this effect, and the optical quality is sufficient for accomplishing the science goals of the mission.

NASA's Lucy mission launched last year on its trip to the Trojan asteroids, located in the orbit of Jupiter. Despite an issue with one of its solar arrays, the spacecraft has been traveling as hoped and is on its way to study the ancient asteroids with the aim to learn more about how the solar system formed. Now, NASA has shared some of the first images taken by Lucy's instruments as part of their calibration process.

Lucy has a total of four cameras, including the two twin Terminal Tracking Cameras (T2CAM), which have a wide field of view and are used to lock onto asteroids and point the other instruments in the right direction as Lucy performs close flybys of them. The other cameras are the Multicolor Visible Imaging Camera (MVIC) which will take panorama-like images, and the Long-Range Reconnaissance Imager (L’LORRI) which will take high-resolution, up-close images of the asteroids. In addition to its cameras, Lucy also has a spectrometer and an instrument for mapping temperature.

Read more