“Learning physics-based motion style with nonlinear inverse optimization” by Liu, Hertzmann and Popovic

  • ©C. Karen Liu, Aaron Hertzmann, and Zoran Popovic




    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. Alexander, R. M. 1988. Elastic Mechanisms in Animal Movement. Cambridge University Press.Google Scholar
    2. Alexander, R. M. 2001. Design By Numbers. Nature 412 (Aug.), 591.Google ScholarCross Ref
    3. Arikan, O., and Forsyth, D. A. 2002. Synthesizing Constrained Motions from Examples. ACM Transactions on Graphics 21, 3 (July), 483–490. (Proceedings of ACM SIGGRAPH 2002). Google ScholarDigital Library
    4. Arikan, O., Forsyth, D. A., and O’Brien, J. F. 2003. Motion synthesis from annotations. ACM Transactions on Graphics 22, 3 (July), 402–408. Google ScholarDigital Library
    5. Bhat, K. S., Seitz, S. M., Popović, J., and Khosla, P. K. 2002. Computing the physical parameters of rigid-body motion from video. Lecture Notes in Computer Science 2350, 551–566. Google ScholarDigital Library
    6. Bhat, K. S., Twigg, C. D., Hodgins, J. K., Khosla, P. K., Popović, Z., and Seitz, S. M. 2003. Estimating cloth simulation parameters from video. In Eurographics/SIGGRAPH Symposium on Computer Animation, ACM Press, 37–51. Google ScholarDigital Library
    7. Brand, M., and Hertzmann, A. 2000. Style machines. Proceedings of SIGGRAPH 2000 (July), 183–192. Google ScholarDigital Library
    8. De Leva, P. 1996. Adjustments to Zatsiorsky-Seluyanov’s segment inertia parameters. J. of Biomechanics 29, 9, 1223–1230.Google ScholarCross Ref
    9. Faloutsos, P., Van De Panne, M., and Terzopoulos, D. 2001. Composable Controllers for Physics-Based Character Animation. In Proceedings of SIGGRAPH 2001, 251–260. Google ScholarDigital Library
    10. Fang, A. C., and Pollard, N. S. 2003. Efficient synthesis of physically valid human motion. ACM Transactions on Graphics 22, 3 (July), 417–426. Google ScholarDigital Library
    11. Farley, C. T., and Morgenroth, D. C. 1999. Leg Stiffness Primarily Depends on Ankle Stiffness During Human Hopping. Journal of Biomechanics 32, 267–273.Google ScholarCross Ref
    12. Ferris, D. P., Liang, K., and Farley, C. T. 1999. Runners Adjust Leg Stiffness for Their First Step on a New Running Surface. Journal of Biomechanics 32, 787–794.Google ScholarCross Ref
    13. Full, R. J., Kubow, T., Schmitt, J., Holmes, P., and Koditschek, D. 2002. Quantifying dynamic stability and maneuverability in legged locomotion. Integ. and Comp. Biol 42, 129–157.Google ScholarCross Ref
    14. Geyer, C. J., and Thompson, E. A. 1992. Constrained Monte Carlo maximum likelihood for dependent data. J. Roy. Statist. Soc. Ser. B 54, 657–699.Google Scholar
    15. Gill, P., Saunders, M., and Murray, W. 1996. SNOPT: An SQP algorithm for large-scale constrained optimization. Tech. Rep. NA 96-2, University of California, San Diego.Google Scholar
    16. Gleicher, M. 1998. Retargeting Motion to New Characters. Proceedings of SIGGRAPH 98 (July), 33–42. Google ScholarDigital Library
    17. Grassia, F. S. 1998. Practical parameterization of rotations using the exponential map. Journal of Graphics Tools 3, 3, 29–48. Google ScholarDigital Library
    18. Grochow, K., Martin, S. L., Hertzmann, A., and Popović, Z. 2004. Style-based Inverse Kinematics. ACM Transactions on Graphics (Aug.), 522–531. Google ScholarDigital Library
    19. Grzeszczuk, R., Terzopoulos, D., and Hinton, G. 1998. NeuroAnimator: Fast Neural Network Emulation and Control of Physics-Based Models. Proceedings of SIGGRAPH 98 (July), 9–20. Google ScholarDigital Library
    20. He, J., Kram, R., and McMahon, T. A. 1991. Mechanics of running under simulated low gravity. J. of Applied Physiology 71, 863–870.Google ScholarCross Ref
    21. Heuberger, C. 2004. Inverse Combinatorial Optimization: A Survey on Problems. Methods, and Results. J. Comb. Optim. 8, 329–361.Google ScholarCross Ref
    22. Hinton, G. E., and Sejnowski, T. J. 1986. Learning and relearning in Boltzmann machines. In Parallel Distributed Processing, Volume 1: Foundations, D. E. Rumelhart and J. L. McClelland, Eds. 282–317. Google ScholarDigital Library
    23. Hinton, G. E. 2002. Training Products of Experts by Minimizing Contrastive Divergence. Neural Computation 14, 8. 1771–1800. Google ScholarDigital Library
    24. Hodgins, J. K., and Pollard, N. S. 1997: Adapting Simulated Behaviors For New Characters. Proc. SIGGRAPH 97, 153–162. Google ScholarDigital Library
    25. Hodgins, J. K., Wooten. W. L., Brogan, D. C., and O’Brien, J. F. 1995. Animating Human Athletics. Proc. SIGGRAPH 95 (August). 71–78. Google ScholarDigital Library
    26. Kovar, L., and Gleicher. M. 2004. Automated Extraction and Parameterization of Motions in Large Data Sets. ACM Transactions on Graphics (Aug.), 559–568. Google ScholarDigital Library
    27. Kovar, L., Gleicher. M., and Pighin, F. 2002. Motion Graphs. ACM Transactions on Graphics 21, 3 (July), 473–482. (Proceedings of ACM SIGGRAPH 2002). Google ScholarDigital Library
    28. Laszlo, J., Van De Panne, M., and Fiume, E. L. 2000. Interactive Control For Physically-Based Animation. Proceedings of SIGGRAPH 2000 (July). 201–208. Google ScholarDigital Library
    29. Lecun, Y., and Huang, F. 2005. Loss Functions for Discriminative Training of Energy-Based Models. In Proc. AIStats.Google Scholar
    30. Lee, J., Chai, J., Reitsma, P. S. A., Hodgins, J. K., and Pollard, N. S. 2002. Interactive Control of Avatars Animated With Human Motion Data. ACM Transactions on Graphics 21, 3 (July), 491–500. (Proceedings of ACM SIGGRAPH 2002). Google ScholarDigital Library
    31. Li, Y., Wang, T., and Shum, H.-Y. 2002. Motion Texture: A Two-Level Statistical Model for Character Motion Synthesis. ACM Transactions on Graphics 21, 3 (July), 465–472. Google ScholarDigital Library
    32. Liu, C. K., and Popović, Z. 2002. Synthesis of Complex Dynamic Character Motion from Simple Animations. ACM Transactions on Graphics 21, 3 (July), 408–416. Proceedings of ACM SIGGRAPH 2002. Google ScholarDigital Library
    33. Liu, Z., Gortler, S. J., and Cohen, M. F. 1994, Hierarchical spacetime control. In Computer Graphics (SIGGRAPH 94 Proceedings), 35–42. Google ScholarDigital Library
    34. Mount, F. E., Whitmore, M., and Stealey, S. L. 2003. Evaluation of Neutral Body Posture on Shuttle Mission STS-57 (SPACEHAB-1). Tech. Rep. TM-2003-104805, NASA, Feb.Google Scholar
    35. Neff, M., and Fiume, E. 2002. Modeling Tension and Relaxation for Computer Animation. In ACM SIGGRAPH Symposium on Computer Animation, 81–88. Google ScholarDigital Library
    36. Pandy, M. G. 2001. Computer Modeling and Simulation of Human Movement. Annu. Rev. Biomed. Eng. 3, 245–273.Google ScholarCross Ref
    37. Pearsall, D., Reid, J., and Ross, R. 1994. Inertial properties of the human trunk of males determined from magnetic resonance imaging. Annals of Biomed. Eng. 22, 692–706.Google ScholarCross Ref
    38. Pollard, N. S., and Reitsma, P. S. A. 2001. Animation of humanlike characters: Dynamic motion filtering with a physically plausible contact model. In Yale Workshop on Adaptive and Learning Systems.Google Scholar
    39. Popović, Z., and Witkin, A. 1999. Physically Based Motion Transformation. Proceedings of SIGGRAPH 99 (Aug.), 11–20. Google ScholarDigital Library
    40. Pullen, K., and Bregler, C. 2002. Motion Capture Assisted Animation: Texturing and Synthesis. ACM Transactions on Graphics 21, 3 (July), 501–508. Proceedings of ACM SIGGRAPH 2002. Google ScholarDigital Library
    41. Raibert, M. H., and Hodgins, J. K. 1991. Animation of dynamic legged locomotion. In Computer Graphics (SIGGRAPH 91 Proceedings), vol. 25, 349–358. Google ScholarDigital Library
    42. Rose, C., Guenter, B., Bodenheimer, B., and Cohen, M. 1996. Efficient generation of motion transitions using spacetime constraints. In Computer Graphics (SIGGRAPH 96 Proceedings), 147–154. Google ScholarDigital Library
    43. Rose, C., Cohen, M. F., and Bodenheimer, B. 1998. Verbs and Adverbs: Multidimensional Motion Interpolation. IEEE Computer Graphics & Applications 18, 5, 32–40. Google ScholarDigital Library
    44. Safonova, A., Hodgins, J. K., and Pollard, N. S. 2004. Synthesizing Physically Realistic Human Motion in Low-Dimensional Behavior-Specific Spaces. ACM Transactions on Graphics (Aug.). Google ScholarDigital Library
    45. Sun, H. C., and Metaxas, D. N. 2001. Automating gait animation. In Proceedings of ACM SIGGRAPH 2001, Computer Graphics Proceedings, Annual Conference Series, 261–270. Google ScholarDigital Library
    46. Tak, S., and Ko, H.-S. 2005. A physically-based motion retargeting filter. ACM Trans. Graphics 24, 1 (Jan.), 98–117. Google ScholarDigital Library
    47. Torkos, N., and Van De Panne, M. 1998. Footprint-based Quadruped Motion Synthesis. In Graphics Interface ’98, 151–160.Google Scholar
    48. Unuma, M., Anjyo, K., and Takeuchi, R. 1995. Fourier Principles for Emotion-based Human Figure Animation. In Proc. SIGGRAPH 95, 91–96. Google ScholarDigital Library
    49. Van De Panne, M., and Fiume, E. 1993. Sensor-actuator networks. In Computer Graphics (SIGGRAPH 93 Proceedings), vol. 27, 335–342. Google ScholarDigital Library
    50. Van De Panne, M., Kim, R., and Fiume, E. 1994. Virtual Wind-up Toys for Animation. Graphics Interface ’94 (May), 208–215. Held in Banff, Alberta, Canada.Google Scholar
    51. Vasilescu, M. A. O. 2002. Human Motion Signatures: Analysis, Synthesis, Recognition. Proc. ICPR ’02 3 (Aug.), 456–460. Google ScholarDigital Library
    52. Witkin, A., and Kass, M. 1988. Spacetime constraints. In Computer Graphics (SIGGRAPH 88 Proceedings), vol. 22, 159–168. Google ScholarDigital Library
    53. Witkin, A., and Popović, Z. 1995. Motion Warping. Proceedings of SIGGRAPH 95 (Aug.), 105–108. Google ScholarDigital Library

ACM Digital Library Publication:

Overview Page: