Multi-character Motion Retargeting for Large-Scale Transformations

  • Maryam NaghizadehEmail author
  • Darren Cosker
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11542)


Unlike single-character motion retargeting, multi-character motion retargeting (MCMR) algorithms should be able to retarget each character’s motion correcly while maintaining the interaction between them. Existing MCMR solutions mainly focus on small scale changes between interacting characters. However, many retargeting applications require large-scale transformations. In this paper, we propose a new algorithm for large-scale MCMR. We build on the idea of interaction meshes, which are structures representing the spatial relationship among characters. We introduce a new distance-based interaction mesh that embodies the relationship between characters more accurately by prioritizing local connections over global ones. We also introduce a stiffness weight for each skeletal joint in our mesh deformation term, which defines how undesirable it is for the interaction mesh to deform around that joint. This parameter increases the adaptability of our algorithm for large-scale transformations and reduces optimization time considerably. We compare the performance of our algorithm with current state-of-the-art MCMR solution for several motion sequences under four different scenarios. Our results show that our method not only improves the quality of retargeting, but also significantly reduces computation time.


Motion retargeting Computer animation Character interaction Mesh deformation Joint stiffness Space-time optimization 


  1. 1.
    Alexa, M.: Differential coordinates for local mesh morphing and deformation. Vis. Comput. 19(2), 105–114 (2003)zbMATHGoogle Scholar
  2. 2.
    Bernardin, A., Hoyet, L., Mucherino, A., Gonçalves, D., Multon, F.: Normalized Euclidean distance matrices for human motion retargeting. In: Proceedings of the Tenth International Conference on Motion in Games, MIG 2017, pp. 15:1–15:6. ACM, New York (2017)Google Scholar
  3. 3.
    Choi, K.J., Ko, H.S.: Online motion retargetting. J. Vis. Comput. Animation 11(5), 223–235 (2000)CrossRefGoogle Scholar
  4. 4.
    Gleicher, M.: Retargetting motion to new characters. In: Proceedings of the 25th Annual Conference on Computer Graphics and Interactive Techniques, SIGGRAPH 1998, pp. 33–42. ACM, New York (1998)Google Scholar
  5. 5.
    Ho, E.S.L., Chan, J.C.P., Komura, T., Leung, H.: Interactive partner control in close interactions for real-time applications. ACM Trans. Multimedia Comput. Commun. Appl. 9(3), 21:1–21:19 (2013)CrossRefGoogle Scholar
  6. 6.
    Ho, E.S.L., Wang, H., Komura, T.: A multi-resolution approach for adapting close character interaction. In: Proceedings of the 20th ACM Symposium on Virtual Reality Software and Technology, VRST 2014, pp. 97–106. ACM, New York (2014)Google Scholar
  7. 7.
    Ho, E.S., Komura, T., Tai, C.L.: Spatial relationship preserving character motion adaptation. ACM Trans. Graph. (TOG) 29(4), 33 (2010)CrossRefGoogle Scholar
  8. 8.
    Hu, R., van Kaick, O., Wu, B., Huang, H., Shamir, A., Zhang, H.: Learning how objects function via co-analysis of interactions. ACM TOG 35(4), 47:1–47:13 (2016)CrossRefGoogle Scholar
  9. 9.
    Hu, R., Zhu, C., van Kaick, O., Liu, L., Shamir, A., Zhang, H.: Interaction context (icon): towards a geometric functionality descriptor. ACM TOG 34(4), 83:1–83:12 (2015)Google Scholar
  10. 10.
    Jin, T., Kim, M., Lee, S.H.: Aura mesh: motion retargeting to preserve the spatial relationships between skinned characters. Comp. Graph. Forum 37(2), 311–320 (2018)CrossRefGoogle Scholar
  11. 11.
    Kobbelt, L., Campagna, S., Vorsatz, J., Seidel, H.P.: Interactive multi-resolution modeling on arbitrary meshes. In: Proceedings of the 25th Annual Conference on Computer Graphics and Interactive Techniques, SIGGRAPH 1998, pp. 105–114. ACM (1998)Google Scholar
  12. 12.
    Lee, J., Shin, S.Y.: A hierarchical approach to interactive motion editing for human-like figures. In: Proceedings of the 26th Annual Conference on Computer Graphics and Interactive Techniques, SIGGRAPH 1999, pp. 39–48 (1999)Google Scholar
  13. 13.
    Müller, M., Gross, M.: Interactive virtual materials. In: Proceedings of Graphics Interface, GI 2004, pp. 239–246. Canadian Human-Computer Communication Society (2004)Google Scholar
  14. 14.
    Pirk, S., et al.: Understanding and exploiting object interaction landscapes. ACM Trans. Graph. 36(3), 31 (2017)CrossRefGoogle Scholar
  15. 15.
    Si, H., Gärtner, K.: Meshing piecewise linear complexes by constrained delaunay tetrahedralizations. In: Hanks, B.W. (ed.) Proceedings of the 14th International Meshing Roundtable, pp. 147–163. Springer, Heidelberg (2005).
  16. 16.
    Sorkine, O., Alexa, M.: As-rigid-as-possible surface modeling. In: Proceedings of the 5th EG Symposium on Geometry Processing, SGP 2007, pp. 109–116. EG Association (2007)Google Scholar
  17. 17.
    Tak, S., Ko, H.S.: A physically-based motion retargeting filter. ACM Trans. Graph. 24(1), 98–117 (2005)CrossRefGoogle Scholar
  18. 18.
    Villegas, R., Yang, J., Ceylan, D., Lee, H.: Neural kinematic networks for unsupervised motion retargetting. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2018Google Scholar
  19. 19.
    Zhao, X., Choi, M., Komura, T.: Character-object interaction retrieval using the interaction bisector surface. Comput. Graph. Forum 36(2), 119–129 (2017)CrossRefGoogle Scholar
  20. 20.
    Zhao, X., Wang, H., Komura, T.: Indexing 3D scenes using the interaction bisector surface. ACM Trans. Graph. 33(3), 22:1–22:14 (2014)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.University of BathBathUK

Personalised recommendations