Templated Human Motion Synthesis
-
摘要: 为解决现有运动合成方法中控制方式过于复杂的问题,提出一种模板化的运动合成模型,旨在降低运动合成技术的应用门槛.利用稀疏主成分分析(Sparse principal component analysis, SPCA)、Group lasso和Exclusive group lasso对人体运动进行建模,使其对应的每一个低维参数只依赖于少数几个人体关节,构成人体运动的一个内在自由度(Degree of freedom, DOF),并具有直观语义;同时,每个关节被尽量少的低维参数所控制,以减少低维参数对彼此所控制的自由度的交叉影响.实验表明,通过直观地修改低维参数,就能够实时地控制每个参数对应的摆臂幅度、踢腿高度、跳跃距离等运动属性.这种模板学习、模板定制的两步方法,有效地降低了运动合成控制的复杂度,即便非专业人员也可以用其进行艺术创作.Abstract: Since the existing approaches to control human motion synthesis are too complicated, we propose a templated motion synthesis model to reduce the difficulty of using motion synthetic technology. We use sparse principal component analysis(SPCA), group lasso and exclusive group lasso to model human motions so that each low-dimensional parameter depends on a few human joints which form an intrinsic degree of freedom(DOF) with intuitive meanings. Meanwhile, our approach makes each joint controlled by as few low-dimensional parameters as possible to reduce the interferences between different DOFs. Our experiments demonstrate that users can control the motion features like amplitude of swing arm, kick height and jump distance by modifying the low-dimensional parameters intuitively in real time. This two-step approach of template learning and template customization can effectively reduce the complexity of synthesis control, and allows inexperienced users to create a realistic human animation quickly and easily.
-
Key words:
- Motion synthesis /
- template /
- motion parameter /
- semantic feature
-
[1] Zhang Li-Ge, Bi Shu-Sheng, Gao Jin-Lei. Human motion data acquiring and analyzing method for humanoid robot motion designing. Acta Automatica Sinica, 2010, 36(1):107-112(张利格, 毕树生, 高金磊. 仿人机器人复杂动作设计中人体运动数据提取及分析方法. 自动化学报, 2010, 36(1):107-112) [2] [2] Kovar L, Gleicher M, Pighin F. Motion graphs. ACM Transactions on Graphics(TOG), 2002, 21(3):473-482 [3] [3] Kovar L, Gleicher M. Flexible automatic motion blending with registration curves. In:Proceedings of the 2003 ACM SIGGRAPH/Eurographics Symposium on Computer Animation. Switzerland:Eurographics Association, 2003. 214-224 [4] [4] Min J Y, Chen Y L, Chai J X. Interactive generation of human animation with deformable motion models. ACM Transactions on Graphics(TOG), 2009, 29(1):Article No.9 [5] [5] Kwon T, Shin S Y. Motion modeling for on-line locomotion synthesis. In:Proceedings of the 2005 ACM SIGGRAPH/Eurographics Symposium on Computer Animation. Los Angeles, CA, USA:ACM, 2005. 29-38 [6] [6] Heck R, Gleicher M. Parametric motion graphs. In:Proceedings of the 2007 Symposium on Interactive 3D Graphics and Games. Seattle, Washington, USA:ACM, 2007. 129-136 [7] [7] Kovar L, Gleicher M. Automated extraction and parameterization of motions in large data sets. ACM Transactions on Graphics, 2004, 23(3):559-568 [8] [8] Park S I, Shin H J, Kim T H, Shin S Y. On-line motion blending for real-time locomotion generation. Computer Animation and Virtual Worlds, 2004, 15(3-4):125-138 [9] Li Jin-Dan, Mao Tian-Lu, Wang Zhao-Qi, Liu Jin-Gang. Motion graph construction based on parametric motion synthesis. Computer Simulation, 2009, 26(3):208-212(李锦丹, 毛天露, 王兆其, 刘金刚. 基于参数化运动合成的运动图构建及其应用. 计算机仿真, 2009, 26(3):208-212) [10] Shin H J, Lee J. Motion synthesis and editing in low-dimensional spaces. Computer Animation and Virtual Worlds, 2006, 17(3-4):219-227 [11] Wang Yu-Jie, Xiao Jun, Wei Bao-Gang. 3D human motion synthesis based on nonlinear manifold learning. Journal of Image and Graphics, 2010, 15(6):936-943(王宇杰, 肖俊, 魏宝刚. 基于非线性流形学习的3维人体运动合成. 中国图象图形学报, 2010, 15(6):936-943) [12] Liu H, He F, Cai X T, Chen X, Chen Z. Human motion synthesis using window-based local principal component analysis. In:Proceedings of the 12th International Conference on Computer-Aided Design and Computer Graphics(CAD/Graphics). Washington D.C., USA:IEEE, 2011. 282-287 [13] Zou H, Hastie T, Tibshirani R. Sparse principal component analysis. Journal of Computational and Graphical Statistics, 2006, 15(2):265-286 [14] Yuan M, Lin Y. Model selection and estimation in regression with grouped variables. Journal of the Royal Statistical Society:Series B(Statistical Methodology), 2006, 68(1):49-67 [15] Chen X Y, Yuan X T, Yan S C, Tang J H, Rui Y, Chua T S. Towards multi-semantic image annotation with graph regularized exclusive group lasso. In:Proceedings of the 19th ACM International Conference on Multimedia. New York, NY, USA:ACM, 2011. 263-272 [16] Gleicher M, Shin H J, Kovar L, Jepsen A. Snap-together motion:assembling run-time animations. In:Proceedings of the ACM SIGGRAPH 2008 Classes. New York:ACM, 2008:Article No.52 [17] Kwon T, Shin S Y. Motion modeling for on-line locomotion synthesis. In:Proceedings of the 2005 ACM SIGGRAPH/Eurographics Symposium on Computer Animation. New York, NY, USA:ACM, 2005. 29-38 [18] Safonova A, Hodgins J K, Pollard N S. Synthesizing physically realistic human motion in low-dimensional, behavior-specific spaces. ACM Transactions on Graphics(TOG), 2004, 23(3):514-521 [19] Li Chun-Peng, Wang Zhao-Qi, Xia Shi-Hong. Motion synthesis for virtual human using functional data analysis. Journal of Software, 2009, 20(6):1664-1672(李淳芃, 王兆其, 夏时洪. 人体运动的函数数据分析与合成. 软件学报, 2009, 20(6):1664-1672) [20] Liu Geng-Dai, Xu Ming-Liang, Zhang Ming-Min. Human motion synthesis based on independent spatio-temporal feature space. Chinese Journal of Computers, 2011, 34(3):464-472(刘更代, 徐明亮, 张明敏. 基于独立时空特征空间的人体运动合成. 计算机学报, 2011, 34(3):464-472) [21] Lan Rong-Yi, Sun Huai-Jiang. Style analysis and human locomotion synthesis based on inverse kinematics and reconstructive ICA. Acta Automatica Sinica, 2014, 40(6):1135-1147(蓝荣祎, 孙怀江. 基于逆运动学和重构式ICA的人体运动风格分析与合成. 自动化学报, 2014, 40(6):1135-1147) [22] Lan Rong-Yi, Sun Huai-Jiang. A sparse semantic parametric model for interactive motion synthesis. Journal of Computer-Aided Design Computer Graphics, 2013, 25(3):341-349(蓝荣祎, 孙怀江. 人体运动的稀疏语义参数化模型与交互式合成. 计算机辅助设计与图形学学报, 2013, 25(3):341-349) [23] Hoerl A E, Kennard R W. Ridge regression:biased estimation for nonorthogonal problems. Technometrics, 1970, 12(1):55-67 [24] Zou H, Hastie T. Regularization and variable selection via the elastic net. Journal of the Royal Statistical Society:Series B(Statistical Methodology), 2005, 67(2):301-320 [25] Zhou Y, Jin R, Hoi S C H. Exclusive lasso for multi-task feature selection. IN:Proceedings of the 2010 International Conference on Artificial Intelligence and Statistics. 2010. 988-995 [26] Sakoe H, Chiba S. Dynamic programming algorithm optimization for spoken word recognition. IEEE Transactions on Acoustics, Speech, and Signal Processing, 1978, 26(1):43-49 [27] Nesterov Y. Smooth minimization of non-smooth functions. Mathematical Programming, 2005, 103(1):127-152 [28] Tseng P. On accelerated proximal gradient methods for convex-concave optimization. SIAM Journal on Optimization, 2008.
点击查看大图
计量
- 文章访问数: 1647
- HTML全文浏览量: 99
- PDF下载量: 1908
- 被引次数: 0