The Community for Technology Leaders
2017 IEEE Virtual Reality (VR) (2017)
Los Angeles, CA, USA
March 18, 2017 to March 22, 2017
ISSN: 2375-5334
ISBN: 978-1-5090-6648-3
pp: 131-140
Charles Malleson , Disney Research, UK
Maggie Kosek , Disney Research, UK
Martin Klaudiny , Disney Research, UK
Ivan Huerta , Disney Research, UK
Jean-Charles Bazin , Disney Research, CH
Alexander Sorkine-Hornung , Disney Research, CH
Mark Mine , Walt Disney Imagineering, USA
Kenny Mitchell , Disney Research, UK
ABSTRACT
We present a system for rapid acquisition of bespoke, animatable, full-body avatars including face texture and shape. A blendshape rig with a skeleton is used as a template for customization. Identity blendshapes are used to customize the body and face shape at the fitting stage, while animation blendshapes allow the face to be animated. The subject assumes a T-pose and a single snapshot is captured using a stereo RGB plus depth sensor rig. Our system automatically aligns a photo texture and fits the 3D shape of the face. The body shape is stylized according to body dimensions estimated from segmented depth. The face identity blendweights are optimised according to image-based facial landmarks, while a custom texture map for the face is generated by warping the input images to a reference texture according to the facial landmarks. The total capture and processing time is under 10 seconds and the output is a light-weight, game-engine-ready avatar which is recognizable as the subject. We demonstrate our system in a VR environment in which each user sees the other users' animated avatars through a VR headset with real-time audio-based facial animation and live body motion tracking, affording an enhanced level of presence and social engagement compared to generic avatars.
INDEX TERMS
Face, Avatars, Cameras, Three-dimensional displays, Shape, Solid modeling, Animation
CITATION

C. Malleson et al., "Rapid one-shot acquisition of dynamic VR avatars," 2017 IEEE Virtual Reality (VR), Los Angeles, CA, USA, 2017, pp. 131-140.
doi:10.1109/VR.2017.7892240
93 ms
(Ver 3.3 (11022016))