Synthesis and editing of personalized stylistic human motion

This paper presents a generative human motion model for synthesis, retargeting, and editing of personalized human motion styles. We first record a human motion database from multiple actors performing a wide variety of motion styles for particular actions. We then apply multilinear analysis techniques to construct a generative motion model of the form x = g(a, e) for particular human actions, where the parameters a and e control "identity" and "style" variations of the motion x respectively. The new modular representation naturally supports motion generalization to new actors and/or styles. We demonstrate the power and flexibility of the multilinear motion models by synthesizing personalized stylistic human motion and transferring the stylistic motions from one actor to another. We also show the effectiveness of our model by editing stylistic motion in style and/or identity space.

[1]  Lucas Kovar,et al.  Flexible automatic motion blending with registration curves , 2003, SCA '03.

[2]  Yong Cao,et al.  Style components , 2006, Graphics Interface.

[3]  Hanspeter Pfister,et al.  Face transfer with multilinear models , 2005, ACM Trans. Graph..

[4]  L. Tucker,et al.  Some mathematical notes on three-mode factor analysis , 1966, Psychometrika.

[5]  Zoran Popovic,et al.  Physically based motion transformation , 1999, SIGGRAPH.

[6]  Aaron Hertzmann,et al.  Style machines , 2000, SIGGRAPH 2000.

[7]  Jovan Popovic,et al.  Style translation for human motion , 2005, ACM Trans. Graph..

[8]  N. Troje.  Decomposing biological motion: a framework for analysis and synthesis of human gait patterns. , 2002, Journal of vision.

[9]  Narendra Ahuja,et al.  Out-of-core tensor approximation of multi-dimensional matrices of visual data , 2005, ACM Trans. Graph..

[10]  Tomohiko Mukai,et al.  Geostatistical motion interpolation , 2005, SIGGRAPH '05.

[11]  Okan Arikan,et al.  Interactive motion generation from examples , 2002, ACM Trans. Graph..

[12]  M. Alex O. Vasilescu.  Human motion signatures: analysis, synthesis, recognition , 2002, Object recognition supported by user interaction for service robots.

[13]  J. Hodgins,et al.  Construction and optimal search of interpolated motion graphs , 2007, SIGGRAPH 2007.

[14]  Lucas Kovar,et al.  Automated extraction and parameterization of motions in large data sets , 2004, ACM Trans. Graph..

[15]  Jehee Lee,et al.  Motion patches: buildings blocks for virtual environments annotated with motion data , 2005, SIGGRAPH 2005.

[16]  Yen-Lin Chen,et al.  Flexible registration of human motion data with parameterized motion models , 2009, I3D '09.

[17]  Michael Gleicher,et al.  Automated extraction and parameterization of motions in large data sets , 2004, SIGGRAPH 2004.

[18]  Jessica K. Hodgins,et al.  Performance animation from low-dimensional control signals , 2005, ACM Trans. Graph..

[19]  C. Karen Liu,et al.  Learning physics-based motion style with nonlinear inverse optimization , 2005, ACM Trans. Graph..

[20]  Lucas Kovar,et al.  Motion graphs , 2002, SIGGRAPH Classes.

[21]  Tomohiko Mukai,et al.  Multilinear Motion Synthesis with Level-of-Detail Controls , 2007, 15th Pacific Conference on Computer Graphics and Applications (PG'07).

[22]  Jessica K. Hodgins,et al.  Interactive control of avatars animated with human motion data , 2002, SIGGRAPH.

[23]  Kenji Amaya,et al.  Emotion from Motion , 1996, Graphics Interface.

[24]  Harry Shum,et al.  Motion texture: a two-level statistical model for character motion synthesis , 2002, ACM Trans. Graph..

[25]  Lucas Kovar,et al.  Motion Graphs , 2002, ACM Trans. Graph..

[26]  Michael Gleicher,et al.  Retargetting motion to new characters , 1998, SIGGRAPH.

[27]  Aaron Hertzmann,et al.  Style-based inverse kinematics , 2004, ACM Trans. Graph..

[28]  J. Leeuw,et al.  Principal component analysis of three-mode data by means of alternating least squares algorithms , 1980 .

[29]  N. Ahuja,et al.  Out-of-core tensor approximation of multi-dimensional matrices of visual data , 2005, SIGGRAPH 2005.

[30]  Aaron Hertzmann,et al.  Style-based inverse kinematics , 2004, SIGGRAPH 2004.

[31]  Taesoo Kwon,et al.  Motion modeling for on-line locomotion synthesis , 2005, SCA '05.

[32]  Michael Gleicher,et al.  Parametric motion graphs , 2007, SI3D.

[33]  Jehee Lee,et al.  Motion patches: building blocks for virtual environments annotated with motion data , 2006, ACM Trans. Graph..

[34]  M. Alex O. Vasilescu,et al.  TensorTextures: multilinear image-based rendering , 2004, SIGGRAPH 2004.

[35]  Sung Yong Shin,et al.  A hierarchical approach to interactive motion editing for human-like figures , 1999, SIGGRAPH.

[36]  Tamara G. Kolda,et al.  Tensor Decompositions and Applications , 2009, SIAM Rev..

[37]  David J. Fleet,et al.  Multifactor Gaussian process models for style-content separation , 2007, ICML '07.

[38]  Yen-Lin Chen,et al.  Interactive generation of human animation with deformable motion models , 2009, TOGS.

[39]  Jessica K. Hodgins,et al.  Constraint-based motion optimization using a statistical dynamic model , 2007, ACM Trans. Graph..

[40]  Michael F. Cohen,et al.  Verbs and Adverbs: Multidimensional Motion Interpolation , 1998, IEEE Computer Graphics and Applications.

[41]  Jessica K. Hodgins,et al.  Construction and optimal search of interpolated motion graphs , 2007, ACM Trans. Graph..