The appearance of reality is paramount in the world of make-believe, where the viewing public yearns for animated characters who walk, run, twist and turn like real people and display a full range of human emotions and expressions.
With those goals in mind, two research teams from Carnegie Mellon University and Disney Research Pittsburgh are busy developing computer techniques that quickly produce realistic animated facial expressions and body motions -- a real challenge given the myriad capabilities of the face's 43 muscles, the complexity of the human body and our ability to perceive subtle changes in human motion.
The facial expression and body movement projects are in the research-and-development phase, but they promise animators more advanced tools to make characters appear more human-like.
Facial expression
One CMU-Disney team is basing facial animations on the best available prototype -- an actual human face.
For now, to animate faces, modern animators must sculpt different emotional expressions and film 3-D models of them. Then the animator blends those expressions together to emulate facial motion.
But Rafael Tena at Disney Research Pittsburgh has produced a method, with help from Carnegie Mellon's Robotics Institute, to capture the motion of an actual actor's face as he or she reads a script and makes dramatic expressions.
By following 13 programmed geometric regions on the face along with a computer program that links certain muscular motions, the new method can generate animated emotions and facial movements that could be far superior than anything currently available.
"Traditionally people who do movies with animated characters use a lot of talented 3-D modelers who sculpt one figure with a mouth open and one with [raised] eyebrows and all the different models with 200 to 300 that can be blended into motion," Mr. Tena said. "We get data from a real actor and define different regions of the face to create a model that allows us to control the face with poses, without having to go through a modeler. Rather than do poses from a sculpture, we develop models from real data."
To make this method of "motion capture" work, the computer analyzes motion in the 13 areas based on which points move in concert and which move independently. The computer program analyzes the subtle motions of the actor's face and produces an animated face replicating them.
Mr. Tena is working with Fernando De La Torre from CMU's Robotics Institute and Iain Matthews, a senior research scientist with Disney Research Pittsburgh to develop the technology.
"Anything we are doing in our lab is to try to focus on topics with potential value for the Disney company," he said.
Body movement
In a simultaneous project, Disney Research Pittsburgh is developing processes to capture real-life body motion for animation in everyday environments. That's where Yaser Sheikh comes in.
In the existing process, animators put actors in form-fitting outfits with white dots and record the actors as they move around in a lab. The cameras document the motion of the white dots, which a computer then analyzes to create similar moves for an animated character.
But Mr. Sheikh, an assistant research professor at CMU's Robotics Institute and the Quality of Life Technology Center, and his team decided to switch the process around.
Instead of having the cameras film the actor, they have attached 19 cameras to the actor's clothes so the cameras document the body motion in relationship to fixed points in the surrounding environment.
As the body moves, the cameras record the size of the motion and feed the data to a computer programmed to analyze the range of motions possible for humans. The computer considers all the data from the cameras to produce the most plausible way the body was moving. When that data is applied to an animated figure, the result is animated motion that replicates the actor's movements, creating accurate motion when the animated figure walks, jumps or gesticulates.
This process allows an actor to walk anywhere, rather than be confined to a laboratory. It also uses everyday cameras that Mr. Sheikh and fellow researchers Takaaki Shiratori, Hyun Soo Park, Leonid Sigal and Jessica Hodgins hope someday to be smaller and fit into clothing so that the average person can produce animations or record movements wherever he or she goes.
Because the environment doesn't have to be covered in cameras, the team can capture animations of sports and other activities that are hard to perform in the laboratory.
The body-motion technology also could be used to analyze how people undergoing rehabilitation or using prosthetic limbs are walking. Researchers also see potential applications in sports to analyze athletic performances.





Comments
Welcome to Post-Gazette subscriber-only commenting community. Please review our community guidelines.