Abstract
In this article, we will formulate a mathematical framework that allows us to treat character animations as points on infinite-dimensional Hilbert manifolds. Constructing geodesic paths between animations on those manifolds allows us to derive a distance function to measure similarities of different motions. This approach is derived from the field of geometric shape analysis, where such formalisms have been used to facilitate object recognition tasks. Analogously to the idea of shape spaces, we construct motion spaces consisting of equivalence classes of animations under reparametrizations. Especially cyclic motions can be represented elegantly in this framework. We demonstrate the suitability of this approach in multiple applications in the field of computer animation. First, we show how visual artefacts in cyclic animations can be removed by applying a computationally efficient manifold projection method. We next highlight how geodesic paths can be used to calculate interpolations between various animations in a computationally stable way. Finally, we show how the same mathematical framework can be used to perform cluster analysis on large motion capture databases, which can be used for or as part of motion retrieval problems.
Similar content being viewed by others
Notes
Such as arclength parametrization, open/closed curves etc.
Cyclic animations are periodic, i.e., they can be repeated continuously, such as for example a walking motion.
The root bone can also have rotational and translational transformations with respect to a global coordinate system.
i.e., translation w.r.t to its parent.
By a bone’s degrees of freedom we mean, more precisely, the corresponding joint’s degrees of freedom.
Also known as elastic metric.
They are parametrized by weights balancing the influences of bending vs. stretching forces.
See Fig. 2
We could also construct a similar space over the space of open curves \(\mathcal {C}^o\), where the start point remains fixed but the sampling rate along the curve varies.
See also the attached videos.
The Palais-metric; see, e.g., [17].
Corresponding to general and cyclic animations, respectively.
References
Abdelkader, M.F., Abd-Almageed, W., Srivastava, A., Chellappa, R.: Silhouette-based gesture and action recognition via modeling trajectories on riemannian shape manifolds. Computer Vis. Image Underst. 115(3), 439–455 (2011). doi:10.1016/j.cviu.2010.10.006. http://www.sciencedirect.com/science/article/pii/S1077314210002377
Bauer, M., Bruveris, M., Michor, P.: Overview of the geometries of shape spaces and diffeomorphism groups. J. Math. Imaging Vis., pp. 1–38 (2014). doi:10.1007/s10851-013-0490-z
Bauer, M., Harms, P., Michor, P.W.: Sobolev metrics on shape space of surfaces. J. Geometr. Mech. 3(4), 389–438 (2011)
Bruderlin, A., Williams, L.: Motion signal processing. In: Proceedings of the 22nd Annual Conference on Computer Graphics and Interactive Techniques, p. 97104. ACM (1995)
CMU: Carnegie-mellon mocap database. http://mocap.cs.cmu.edu/ (2003). Accessed 27 June 2014
González Castro, G., Athanasopoulos, M., Ugail, H.: Cyclic animation using partial differential equations. Vis. Computer 26(5), 325–338 (2010). doi:10.1007/s00371-010-0422-5
Kilian, M., Mitra, N.J., Pottmann, H.: Geometric modeling in shape space. ACM Trans. Graph. (SIGGRAPH) 26(3), #64, 1–8 (2007)
Klassen, E., Srivastava, A., Mio, M., Joshi, S.: Analysis of planar shapes using geodesic paths on shape spaces. IEEE Trans. Pattern Anal. Mach. Intell. 26(3), 372–383 (2004). doi:10.1109/TPAMI.2004.1262333
Kovar, L., Gleicher, M.: Flexible automatic motion blending with registration curves. In: Proceedings of the 2003 ACM SIGGRAPH/Eurographics Symposium on Computer Animation, SCA ’03, p. 214224. Eurographics Association, Aire-la-Ville, Switzerland, Switzerland (2003). http://dl.acm.org/citation.cfm?id=846276.846307
Kovar, L., Gleicher, M., Pighin, F.: Motion graphs. ACM Trans. Graph. 21(3), 473–482 (2002). doi:10.1145/566654.566605
Kurtek, S., Klassen, E., Ding, Z., Srivastava, A.: A novel riemannian framework for shape analysis of 3D objects. In: 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1625–1632 (2010). doi:10.1109/CVPR.2010.5539778
Kurtek, S., Srivastava, A., Klassen, E., Ding, Z.: Statistical modeling of curves using shapes and related features. J. Am. Stat. Assoc. 107(499), 1152–1165 (2012)
Liu, W.: A riemannian framework for annotated curves analysis. Ph.D. Thesis, The Florida State University . http://diginole.lib.fsu.edu/etd/4997 (2011)
Liu, W., Srivastava, A., Zhang, J.: A mathematical framework for protein structure comparison. PLoS Comput. Biol. 7(2), e1001,075 (2011). doi:10.1371/journal.pcbi.1001075
Milnor, J.W.: Morse Theory (AM-51), vol. 51. Princeton University Press, Princeton (1963)
Ormoneit, D., Black, M.J., Hastie, T., Kjellström, H.: Representing cyclic human motion using functional analysis. Image Vis. Comput. 23(14), 1264–1276 (2005). doi:10.1016/j.imavis.2005.09.004
Palais, R.S.: Morse theory on hilbert manifolds. Topology 2(4), 299–340 (1963). doi:10.1016/0040-9383(63),90013-2. http://www.sciencedirect.com/science/article/pii/0040938363900132
Pejsa, T., Pandzic, I.: State of the art in example-based motion synthesis for virtual characters in interactive applications. Computer Graph. Forum 29(1), 202–226 (2010). doi:10.1111/j.1467-8659.2009.01591.x
Shoemake, K.: Animating rotation with quaternion curves. SIGGRAPH Comput. Graph. 19(3), 245–254 (1985). doi:10.1145/325165.325242
Srivastava, A., Klassen, E., Joshi, S., Jermyn, I.: Shape analysis of elastic curves in euclidean spaces. IEEE Trans. Pattern Anal. Mach. Intell. 33(7), 1415–1428 (2011). doi:10.1109/TPAMI.2010.184
Srivastava, A., Turaga, P., Kurtek, S.: On advances in differential-geometric approaches for 2D and 3D shape analyses and activity recognition. Image Vis. Comput. 30(67), 398–416 (2012). doi:10.1016/j.imavis.2012.03.006. http://www.sciencedirect.com/science/article/pii/S0262885612000492
Younes, L.: Spaces and manifolds of shapes in computer vision: an overview. Image Vis. Comput. 30(67), 389–397 (2012). doi:10.1016/j.imavis.2011.09.009. http://www.sciencedirect.com/science/article/pii/S0262885611001028
Acknowledgments
The author would like to thank Elena Celledoni and Markus Grasmair for valuable discussions and feedback. This research was supported in part by the GeNuIn Applications project grant from the Research Council of Norway. The data used in this project was obtained from mocap.cs.cmu.edu. The database was created with funding from NSF EIA-0196217.
Author information
Authors and Affiliations
Corresponding author
Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
About this article
Cite this article
Eslitzbichler, M. Modelling character motions on infinite-dimensional manifolds. Vis Comput 31, 1179–1190 (2015). https://doi.org/10.1007/s00371-014-1001-y
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00371-014-1001-y