Using new methodology, researchers have developed a camera that can capture facial expressions -- a key component of visual effects for movies and computer games -- with the robustness of traditional multi-view methods."There has been a trend in facial performance capture toward methods that use fewer cameras and less hardware, giving actors more freedom to perform. But usually that means a trade off in the level of detail and accuracy," said Markus Gross, vice president at Disney Research where the new device has been developed.The Disney team created a model that takes the underlying facial anatomy and skin thickness into account. Moreover, the method has demonstrated the unprecedented ability for a single camera to capture extreme deformations caused by external forces, such as a jet of compressed air forcing a man's cheek to ripple and flutter.
"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," Gross said. The researchers were able to build their models with a minimal number of facial scans and expressions."We believe that our anatomically constrained local deformation model will have a substantial impact on different areas of facial performance capture and animation," said Thabo Beeler, senior research scientist at Disney Research.The researchers will present their model at the ACM International Conference on Computer Graphics and Interactive Techniques (SIGGRAPH) in Anaheim, California, on July 24.