Automatic creation of three-dimensional avatars

被引:4
作者
Villa-Uriol, MC [1 ]
Sainz, M [1 ]
Kuester, F [1 ]
Bagherzadeh, N [1 ]
机构
[1] Univ Calif Irvine, Visualizat & Interact Syst Grp, Dept Elect & Comp Engn, Irvine, CA 92697 USA
来源
VIDEOMETRICS VII | 2003年 / 5013卷
关键词
3D avatars; human body reconstruction; virtual environments;
D O I
10.1117/12.473109
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Highly accurate avatars of humans promise a new level of realism in engineering and entertainment applications, including areas such as computer animated movies, computer game development interactive virtual environments and tele-presence. In order to provide high-quality avatars, new techniques for the automatic acquisition and creation are required. A framework for the capture and construction of arbitrary avatars from image data is presented in this paper. Avatars are automatically reconstructed from multiple static images of a human subject by utilizing image information to reshape a synthetic three-dimensional articulated reference model. A pipeline is presented that combines a set of hardware-accelerated stages into one seamless system. Primary stages in this pipeline include pose estimation, skeleton fitting, body part segmentation, geometry construction and coloring, leading to avatars that can be animated and included into interactive environments. The presented system removes traditional constraints in the initial pose of the captured subject by using silhouette-based modification techniques in combination with a reference model. Results can be obtained in near-real time with very limited user intervention.
引用
收藏
页码:14 / 25
页数:12
相关论文
共 19 条
[1]   Estimating anthropometry and pose from a single uncalibrated image [J].
Barrón, C ;
Kakadiaris, IA .
COMPUTER VISION AND IMAGE UNDERSTANDING, 2001, 81 (03) :269-284
[2]  
Cheung GKM, 2000, PROC CVPR IEEE, P714, DOI 10.1109/CVPR.2000.854944
[3]  
COHEN I, 2001, 5 WORLD MULT SYST CY
[4]  
DAPUZZO N, 1999, P SOC PHOTO-OPT INS, V3461, P36
[5]   Whole-body modelling of people from multiview images to populate virtual worlds [J].
Hilton, A ;
Beresford, D ;
Gentils, T ;
Smith, R ;
Sun, W ;
Illingworth, J .
VISUAL COMPUTER, 2000, 16 (07) :411-436
[6]   Virtual people: Capturing human models to populate virtual worlds [J].
Hilton, A ;
Beresford, D ;
Gentils, T ;
Smith, R ;
Sun, W .
COMPUTER ANIMATION 1999, PROCEEDINGS, 1999, :174-185
[7]   VISUAL-PATTERN RECOGNITION BY MOMENT INVARIANTS [J].
HU, M .
IRE TRANSACTIONS ON INFORMATION THEORY, 1962, 8 (02) :179-&
[8]   Three-dimensional human body model acquisition from multiple views [J].
Kakadiaris, IA ;
Metaxas, D .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 1998, 30 (03) :191-218
[9]   THE VISUAL HULL CONCEPT FOR SILHOUETTE-BASED IMAGE UNDERSTANDING [J].
LAURENTINI, A .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1994, 16 (02) :150-162
[10]  
Lok B., 2001, P 2001 S INT 3D GRAP, P69, DOI DOI 10.1145/364338.364364