Parametric Human Body Reconstruction Based on Sparse Key Points

被引:16
作者
Cheng, Ke-Li [1 ]
Tong, Ruo-Feng [1 ]
Tang, Min [1 ]
Qian, Jing-Ye [1 ]
Sarkis, Michel [2 ]
机构
[1] Zhejiang Univ, Dept Comp Sci, Hangzhou, Zhejiang, Peoples R China
[2] Quacomm Technol Inc, Multimedia R&D & Stand, Munich, CA 92121 USA
关键词
Human body reconstruction; range data; regression; SCAPE modeling; SHAPE;
D O I
10.1109/TVCG.2015.2511751
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
We propose an automatic parametric human body reconstruction algorithm which can efficiently construct a model using a single Kinect sensor. A user needs to stand still in front of the sensor for a couple of seconds to measure the range data. The user's body shape and pose will then be automatically constructed in several seconds. Traditional methods optimize dense correspondences between range data and meshes. In contrast, our proposed scheme relies on sparse key points for the reconstruction. It employs regression to find the corresponding key points between the scanned range data and some annotated training data. We design two kinds of feature descriptors as well as corresponding regression stages to make the regression robust and accurate. Our scheme follows with dense refinement where a pre-factorization method is applied to improve the computational efficiency. Compared with other methods, our scheme achieves similar reconstruction accuracy but significantly reduces runtime.
引用
收藏
页码:2467 / 2479
页数:13
相关论文
共 27 条
[1]   SCAPE: Shape Completion and Animation of People [J].
Anguelov, D ;
Srinivasan, P ;
Koller, D ;
Thrun, S ;
Rodgers, J ;
Davis, J .
ACM TRANSACTIONS ON GRAPHICS, 2005, 24 (03) :408-416
[2]  
Anguelov Dragomir., 2004, T SAIL 2004 100, P33
[3]  
[Anonymous], 2015, Comput Vis Media
[4]  
[Anonymous], 2013, ACM T GRAPHIC
[5]  
Baak A., 2013, Consumer Depth Camerasfor Computer Vision: Research Topics and Applications, P71, DOI DOI 10.1007/978-1-4471-4640-7_5
[6]  
Balan AO, 2008, LECT NOTES COMPUT SC, V5303, P15, DOI 10.1007/978-3-540-88688-4_2
[7]   FaceWarehouse: A 3D Facial Expression Database for Visual Computing [J].
Cao, Chen ;
Weng, Yanlin ;
Zhou, Shun ;
Tong, Yiying ;
Zhou, Kun .
IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS, 2014, 20 (03) :413-425
[8]   3D Shape Regression for Real-time Facial Animation [J].
Cao, Chen ;
Weng, Yanlin ;
Lin, Stephen ;
Zhou, Kun .
ACM TRANSACTIONS ON GRAPHICS, 2013, 32 (04)
[9]  
Cao XD, 2012, PROC CVPR IEEE, P2887, DOI 10.1109/CVPR.2012.6248015
[10]   Deformable model for estimating clothed and naked human shapes from a single image [J].
Chen, Xiaowu ;
Guo, Yu ;
Zhou, Bin ;
Zhao, Qinping .
VISUAL COMPUTER, 2013, 29 (11) :1187-1196