acm-header
Sign In

Communications of the ACM

ACM TechNews

Tiny Motions Bring Digital Doubles to Life


View as: Print Mobile App Share:
Initial results from scans using Motion and Shape Capture software.

Motion and Shape Capture software computes body shape and pose from standard motion capture marker sets. Bodies in purple are estimated from 67 motion capture markers, while scans in green are captured with a high-resolution 3D body scanner. Split-color b

Credit: Perceiving Systems Department, Max Planck Society

New technology dubbed Motion and Shape Capture (MoSh) is helping animators convert moving dots into detailed body shapes that move like real humans.

MoSh was developed by a team of researchers under the direction of Michael J. Black, director of the Max Planck Institute's Perceiving Systems department. The technology enables animators to record people's three-dimensional (3D) motions and shapes and digitally retarget them to a new body shape.

MoSh computes body shape and pose from standard motion capture marker sets, and needs only a small amount of such data to create animations with a high level of realism. A complex mathematical model of human shape and pose is used to compute body shape and motion directly from the 3D marker positions.

The researchers say MoSh's realistic digital human figures may soon be used in video games, training videos, and new virtual-reality headsets.

"Realistically rigging and animating a 3D body requires expertise," says Naureen Mahmood, one of the co-authors of the study. "MoSh will let anyone use motion capture data to achieve results approaching professional animation quality."

Researchers from the Max Planck Institute for Intelligent Systems presented their MoSh study at the recent ACM SIGGRAPH Conference on Computer Graphics and Interactive Techniques in Shenzhen, China.

From Max Planck Society
View Full Article

 

Abstracts Copyright © 2014 Information Inc., Bethesda, Maryland, USA


 

No entries found

Sign In for Full Access
» Forgot Password? » Create an ACM Web Account