DocumentCode :
253672
Title :
Quality Dynamic Human Body Modeling Using a Single Low-Cost Depth Camera
Author :
Qing Zhang ; Bo Fu ; Mao Ye ; Ruigang Yang
Author_Institution :
Univ. of Kentucky, Lexington, KY, USA
fYear :
2014
fDate :
23-28 June 2014
Firstpage :
676
Lastpage :
683
Abstract :
In this paper we present a novel autonomous pipeline to build a personalized parametric model (pose-driven avatar) using a single depth sensor. Our method first captures a few high-quality scans of the user rotating herself at multiple poses from different views. We fit each incomplete scan using template fitting techniques with a generic human template, and register all scans to every pose using global consistency constraints. After registration, these watertight models with different poses are used to train a parametric model in a fashion similar to the SCAPE method. Once the parametric model is built, it can be used as an animitable avatar or more interestingly synthesizing dynamic 3D models from single-view depth videos. Experimental results demonstrate the effectiveness of our system to produce dynamic models.
Keywords :
avatars; cameras; image registration; image sensors; solid modelling; video signal processing; SCAPE method; animitable avatar; autonomous pipeline; dynamic 3D model synthesis; generic human template; global consistency constraints; personalized parametric model; pose-driven avatar; quality dynamic human body modeling; registration; single depth sensor; single low-cost depth camera; single-view depth videos; template fitting techniques; watertight models; Cameras; Iterative closest point algorithm; Joints; Registers; Shape; Solid modeling; Three-dimensional displays; 3D Model; Avatar; Mesh Registration; SCAPE; Template Fitting;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer Vision and Pattern Recognition (CVPR), 2014 IEEE Conference on
Conference_Location :
Columbus, OH
Type :
conf
DOI :
10.1109/CVPR.2014.92
Filename :
6909487
Link To Document :
بازگشت