acm-header
Sign In

Communications of the ACM

ACM TechNews

Single Camera Can Capture High Quality Facial Performance


An actual face, and how the model interprets a deformation to the face.

A new methodology developed by Disney Research uses just one camera to obtain facial performance capture.

Credit: Disney Research

Disney researchers have developed a methodology that uses one camera to obtain facial performance capture, a key component of visual effects for movies and computer games.

The researchers say their single-camera model accounts for the underlying facial anatomy and skin thickness when capturing facial expressions with equal robustness to traditional multi-view methods.

In addition, they say the new method has demonstrated the unprecedented ability for a single camera to capture extreme deformations caused by external forces. "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," says Disney Research's Markus Gross.

The model does not rely on pre-computed facial motions, but instead considers the face's underlying bone structure and skin thickness. "These anatomical factors constrain the face to physically valid expressions and helps counteract depth ambiguities that plague single-camera tracking," says Disney researcher Thabo Beeler.

The researchers demonstrated the single-camera technique using a variety of cameras, including a GoPro camera and an iPhone camera. They presented the anatomically constrained deformation model this week at the ACM SIGGRAPH conference in Anaheim, CA.

From EurekAlert
View Full Article

 

Abstracts Copyright © 2016 Information Inc., Bethesda, Maryland, USA


 

No entries found