Expressive Human Pose Deformation Based on the Rules of Attractive Poses

Conference paper
Part of the Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering book series (LNICST, volume 229)


We propose a method of deforming a human pose based on the rules of attractive poses. In our previous research, we proposed an approach for obtaining the rules of attractive poses from a set of attractive poses with a specific style and another set of unattractive poses by creating a decision tree based on the low-level pose features. In this paper, we propose a heuristic kinematics-based pose deformation method based on the discovered rules of attractive poses. The rules can be applied to any input pose with any specified scale. We evaluated our method through a user experiment. The results show that our method can deform a pose to realize a specified style, although not all rules are applicable to all kinds of poses and an appropriate style and deformation scale must be selected by the user.


Human pose Attractive poses Pose deformation 



This work was supported in part by Grant-in-Aid for Scientific Research (No. 15H02704 and No. 15K05003) from the Japan Society for the Promotion of Science (JSPS).


  1. 1.
    Oshita, M., Yamamura, K., Honda, A.: Finding rules of attractive human poses using decision tree and generating novel attractive poses. In: Computer Graphics International, Article No. 33 (2017)Google Scholar
  2. 2.
    Hoyet, L., Ryall, K., Zibrek, K., Park, H., Lee, J., Hodgins, J., O’sullivan, C.: Evaluating the distinctiveness and attractiveness of human motions on realistic virtual bodies. ACM Trans. Graph. 32(6), 204 (2013). (SIGGRAPH Asia 2013)CrossRefGoogle Scholar
  3. 3.
    Neff, M., Kim, Y.: Interactive editing of motion style using drives and correlations. In: Eurographics/ACM SIGGRAPH Symposium on Computer Animation, pp. 103–112 (2009)Google Scholar
  4. 4.
    Phillips, C.B., Badler, N.I.: Interactive behaviors for bipedal articulated figures. In: SIGGRAPH 1991, pp. 359–362 (2001)Google Scholar
  5. 5.
    Guay, M., Cani, M.P., Ronfard, R.: The line of action: an intuitive interface for expressive character posing. ACM Trans. Graph. 32(6), 205 (2013). (SIGGRAPH Asia 2013)CrossRefGoogle Scholar
  6. 6.
    BOS Action Unity: Action Pose Pictures - Be a Hero! Pie International (2012). (in Japanese)Google Scholar
  7. 7.
    Araki, H.: JoJo’s Bizarre Adventure Comic Series. Shueisha (1987–2017). (in Japanese)Google Scholar
  8. 8.
    Araki, H.: JOJO6251 - The World of Hirohiko Araki. Shueisha (1993). (in Japanese)Google Scholar
  9. 9.
    Yamaguchi, K.: Action Pose 500: Basic Poses. Graphics (2001). (in Japanese)Google Scholar
  10. 10.
    Maar: Dynamic Stop Motion Poses 2: Basic Actoins. Maar (2002). (in Japanese)Google Scholar
  11. 11.
    Kass, G.V.: An exploratory technique for investigating large quantities of categorical data. Appl. Stat. 29(2), 119–127 (1980)CrossRefGoogle Scholar
  12. 12.
    IBM: SPSS statistics ver. 24 (2016)Google Scholar
  13. 13.
    Monheit, G., Badler, N.I.: A kinematic model of the human spine and torso. IEEE Comput. Graph. Appl. 11(2), 29–38 (1991)CrossRefGoogle Scholar
  14. 14.
    Tolani, D., Goswami, A., Badler, N.I.: Real-time inverse kinematics techniques for anthropomorphic limbs. Graph. Models 62(5), 53–388 (2000)CrossRefzbMATHGoogle Scholar

Copyright information

© ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2018

Authors and Affiliations

  1. 1.Kyushu Institute of TechnologyIizukaJapan

Personalised recommendations