Learning physics-based motion style with nonlinear inverse optimization

This paper presents a novel physics-based representation of realistic character motion. The dynamical model incorporates several factors of locomotion derived from the biomechanical literature, including relative preferences for using some muscles more than others. elastic mechanisms at joints due to the mechanical properties of tendons, ligaments, and muscles, and variable stiffness at joints depending on the task. When used in a spacetime optimization framework, the parameters of this model define a wide range of styles of natural human movement.Due to the complexity of biological motion, these style parameters are too difficult to design by hand. To address this, we introduce Nonlinear Inverse Optimization, a novel algorithm for estimating optimization parameters from motion capture data. Our method can extract the physical parameters from a single short motion sequence. Once captured, this representation of style is extremely flexible: motions can be generated in the same style but performing different tasks, and styles may be edited to change the physical properties of the body.

[1]  Geoffrey E. Hinton,et al.  Learning and relearning in Boltzmann machines , 1986 .

[2]  Andrew P. Witkin,et al.  Spacetime constraints , 1988, SIGGRAPH.

[3]  R. M. Alexander,et al.  Elastic mechanisms in animal movement , 1988 .

[4]  Jessica K. Hodgins,et al.  Animation of dynamic legged locomotion , 1991, SIGGRAPH.

[5]  R. Kram,et al.  Mechanics of running under simulated low gravity. , 1991, Journal of applied physiology.

[6]  C. Geyer,et al.  Constrained Monte Carlo Maximum Likelihood for Dependent Data , 1992 .

[7]  Michiel van de Panne,et al.  Sensor-actuator networks , 1993, SIGGRAPH.

[8]  Zicheng Liu,et al.  Hierarchical spacetime control , 1994, SIGGRAPH.

[9]  David C. Brogan,et al.  Animating human athletics , 1995, SIGGRAPH.

[10]  Zoran Popovic,et al.  Motion warping , 1995, SIGGRAPH.

[11]  Ken-ichi Anjyo,et al.  Fourier principles for emotion-based human figure animation , 1995, SIGGRAPH.

[12]  P. Leva.  Adjustments to Zatsiorsky-Seluyanov's segment inertia parameters. , 1996 .

[13]  Michael F. Cohen,et al.  Efficient generation of motion transitions using spacetime constraints , 1996, SIGGRAPH.

[14]  Jessica K. Hodgins,et al.  Adapting simulated behaviors for new characters , 1997, SIGGRAPH.

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

[16]  F. Sebastian Grassia,et al.  Practical Parameterization of Rotations Using the Exponential Map , 1998, J. Graphics, GPU, & Game Tools.

[17]  Michiel van de Panne,et al.  Footprint-based Quadruped Motion Synthesis , 1998, Graphics Interface.

[18]  Geoffrey E. Hinton,et al.  NeuroAnimator: fast neural network emulation and control of physics-based models , 1998, SIGGRAPH.

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

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

[21]  C. T. Farley,et al.  Leg stiffness primarily depends on ankle stiffness during human hopping. , 1999, Journal of biomechanics.

[22]  Daniel P. Ferris,et al.  Runners adjust leg stiffness for their first step on a new running surface. , 1999, Journal of biomechanics.

[23]  Eugene Fiume,et al.  Interactive control for physically-based animation , 2000, SIGGRAPH.

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

[25]  M G Pandy,et al.  Computer modeling and simulation of human movement. , 2001, Annual review of biomedical engineering.

[26]  Dimitris N. Metaxas,et al.  Automating gait generation , 2001, SIGGRAPH.

[27]  Petros Faloutsos,et al.  Composable controllers for physics-based character animation , 2001, SIGGRAPH.

[28]  R. M. Alexander,et al.  Design by numbers , 2001, Nature.

[29]  Daniel Koditschek,et al.  Quantifying Dynamic Stability and Maneuverability in Legged Locomotion1 , 2002, Integrative and comparative biology.

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

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

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

[33]  Christoph Bregler,et al.  Motion capture assisted animation: texturing and synthesis , 2002, ACM Trans. Graph..

[34]  Steven M. Seitz,et al.  Computing the Physical Parameters of Rigid-Body Motion from Video , 2002, ECCV.

[35]  Michael Neff,et al.  Modeling tension and relaxation for computer animation , 2002, SCA '02.

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

[37]  Michael A. Saunders,et al.  SNOPT: An SQP Algorithm for Large-Scale Constrained Optimization , 2002, SIAM J. Optim..

[38]  Geoffrey E. Hinton.  Training Products of Experts by Minimizing Contrastive Divergence , 2002, Neural Computation.

[39]  C. Karen Liu,et al.  Synthesis of complex dynamic character motion from simple animations , 2002, ACM Trans. Graph..

[40]  Nancy S. Pollard,et al.  Efficient synthesis of physically valid human motion , 2003, ACM Trans. Graph..

[41]  David A. Forsyth,et al.  Motion synthesis from annotations , 2003, ACM Trans. Graph..

[42]  Mihriban Whitmore,et al.  Evaluation of Neutral Body Posture on Shuttle Mission STS-57 (SPACEHAB-1). Revision , 2003 .

[43]  Jessica K. Hodgins,et al.  Estimating cloth simulation parameters from video , 2003, SCA '03.

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

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

[46]  Clemens Heuberger,et al.  Inverse Combinatorial Optimization: A Survey on Problems, Methods, and Results , 2004, J. Comb. Optim..

[47]  Jessica K. Hodgins,et al.  Synthesizing physically realistic human motion in low-dimensional, behavior-specific spaces , 2004, SIGGRAPH 2004.

[48]  Hyeong-Seok Ko,et al.  A physically-based motion retargeting filter , 2005, TOGS.

[49]  Yann LeCun,et al.  Loss Functions for Discriminative Training of Energy-Based Models , 2005, AISTATS.

[50]  D. Pearsall,et al.  Inertial properties of the human trunk of males determined from magnetic resonance imaging , 1994, Annals of Biomedical Engineering.