Rapid one-shot acquisition of dynamic VR avatars

Malleson, Charles; Kosek, Maggie; Klaudiny, Martin; Huerta, Ivan; Bazin, Jean-Charles; Sorkine-Hornung, Alexander; Mine, Mark; Mitchell, Kenny

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.

Citation

Malleson, C., Kosek, M., Klaudiny, M., Huerta, I., Bazin, J., Sorkine-Hornung, A., …Mitchell, K. (2017). Rapid one-shot acquisition of dynamic VR avatars. In IEEE 2017 Virtual Reality (VR). https://doi.org/10.1109/vr.2017.7892240

• Conference Name: 2017 IEEE Virtual Reality (VR)
• Conference Location: Los Angeles, US
• Start Date: Mar 18, 2017
• End Date: Mar 22, 2017
• Acceptance Date: Mar 1, 2017
• Online Publication Date: Apr 6, 2017
• Publication Date: Apr 6, 2017
• Deposit Date: Sep 12, 2017
• Publisher: Institute of Electrical and Electronics Engineers
• Series ISSN: 2375-5334
• Book Title: IEEE 2017 Virtual Reality (VR)
• ISBN: 9781509066476
• DOI: https://doi.org/10.1109/vr.2017.7892240
• Keywords: Avatars, capture, virtual reality
• Public URL: http://researchrepository.napier.ac.uk/Output/951398