Skip to main content
SpringerLink
Log in

Learning human shape model from multiple databases with correspondence considering kinematic consensus

  • Original Article
  • Published:
The Visual Computer Aims and scope Submit manuscript

Abstract

In various applications of computer graphics and model-based computer vision, a human shape model cannot only model the kinematic properties of a subject to drive the mesh into various postures, but it can also be utilized to parameterize the shape variations across individuals. It is of great benefit to improve the diversity of the training databases by learning the model from multiple databases, once the correspondences among scans of these databases can be achieved. To accomplish this goal, we proposed a framework to match the scans from multiple databases, using the assistance of kinematic properties, to compute the correspondences. The resulting correspondence is accurate, robust, capable of handling scan incompletion, and is homogeneous across shapes and postures. In our approach, we start with evaluating how a correspondence, which is achieved via minimizing the deformation energy, agrees with the kinematic properties, and then, we jointly fit the source scans to the target scans to derive the correspondences between the databases. The extensive results show that our approach can generate a faithful correspondence even in extreme cases, without carefully selecting the deformation factors and markers. We also developed a method, with which a commendable and predictable result can be synthesized, to control the rendered shape in an intuitive way.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16

Similar content being viewed by others

References

  1. Aiger, D., Mitra, N., Cohen-Or, D.: 4-points congruent sets for robust pairwise surface registration. In: ACM Transactions on Graphics (TOG), vol. 27, p. 85. ACM, New York (2008)

  2. Allen, B., Curless, B., Popović, Z.: The space of human body shapes: reconstruction and parameterization from range scans. In: ACM Transactions on Graphics (TOG), vol. 22, pp. 587–594. ACM, New York (2003)

  3. Anguelov, D., Srinivasan, P., Koller, D., Thrun, S., Rodgers, J., Davis, J.: Scape: shape completion and animation of people. In: ACM Transactions on Graphics (TOG), vol. 24, pp. 408–416. ACM, New York (2005)

  4. Anguelov, D., Srinivasan, P., Pang, H., Koller, D., Thrun, S., Davis, J.: The correlated correspondence algorithm for unsupervised registration of nonrigid surfaces. Adv. Neural Inf. Process. Syst. 17, 33–40 (2005)

    Google Scholar 

  5. Ben Azouz, Z., Shu, C., Mantel, A.: Automatic locating of anthropometric landmarks on 3D human models. (2006)

  6. Chang, W., Zwicker, M.: Automatic registration for articulated shapes. In: Computer Graphics Forum, vol. 27, pp. 1459–1468. Wiley Online Library, New York (2008)

  7. Fischler, M., Bolles, R.: Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM 24(6), 381–395 (1981)

    Article  MathSciNet  Google Scholar 

  8. Gelfand, N., Mitra, N., Guibas, L., Pottmann, H.: Robust global registration. In: Proceedings of the Third Eurographics Symposium on Geometry Processing, pp. 197–206. (2005)

  9. Hasler, N., Stoll, C., Sunkel, M., Rosenhahn, B., Seidel, H.P.: A statistical model of human pose and body shape. In: Dutr’e, P., Stamminger, M. (eds.) Computer Graphics Forum (Proceedings of Eurographics 2008), vol. 2. Munich, Germany (2009)

  10. Huang, Q., Adams, B., Wicke, M., Guibas, L.: Non-rigid registration under isometric deformations. In: Computer Graphics Forum, vol. 27, pp. 1449–1457. Wiley Online Library, New York (2008)

  11. Irani, S., Raghavan, P.: Combinatorial and experimental results for randomized point matching algorithms. Comput. Geom. 12(1–2), 17–31 (1999)

    Article  MATH  MathSciNet  Google Scholar 

  12. James, D., Twigg, C.: Skinning mesh animations. In: ACM Transactions on Graphics (TOG), vol. 24, pp. 399–407. ACM, New York (2005)

  13. Jolliffe, I.: Principal Component Analysis. Wiley Online Library, New York (2005)

  14. Kalogerakis, E., Hertzmann, A., Singh, K.: Learning 3D mesh segmentation and labeling. ACM Trans. Graph. 29(4), 102 (2010)

    Google Scholar 

  15. Kraevoy, V., Sheffer, A.: Cross-parameterization and compatible remeshing of 3d models. In: ACM Transactions on Graphics (TOG), vol. 23, pp. 861–869. ACM, New York (2004)

  16. Kry, P., James, D., Pai, D.: Eigenskin: real time large deformation character skinning in hardware. In: Symposium on Computer Animation: Proceedings of the 2002 ACM SIGGRAPH/Eurographics Symposium on Computer Animation, vol. 21, pp. 153–159 (2002)

  17. Lewis, J., Cordner, M., Fong, N.: Pose space deformation: an unified approach to shape interpolation and skeleton-driven deformation. In: Proceedings of the 27th Annual Conference on Computer Graphics And Interactive Techniques, pp. 165–172. ACM Press/Addison-Wesley Publishing Co., New York (2000)

  18. Li, H., Sumner, R.W., Pauly, M.: Global correspondence optimization for non-rigid registration of depth scans. In: Computer Graphics Forum, vol. 27, pp. 1421–1430. Wiley Online Library, New York (2008)

  19. Lipman, Y., Sorkine, O., Cohen-Or, D., Levin, D., Rossi, C., Seidel, H.: Differential coordinates for interactive mesh editing. In: Shape Modeling Applications, 2004. Proceedings, pp. 181–190. IEEE, New York (2004)

  20. Pekelny, Y., Gotsman, C.: Articulated object reconstruction and markerless motion capture from depth video. In: Computer Graphics Forum, vol. 27, pp. 399–408. Wiley Online Library, New York (2008)

  21. Rusinkiewicz, S., Levoy, M.: Efficient variants of the icp algorithm. In: Third International Conference on 3-D Digital Imaging and Modeling, 2001. Proceedings, pp. 145–152. IEEE, New York (2001)

  22. Shalom, S., Shapira, L., Shamir, A., Cohen-Or, D.: Part analogies in sets of objects. In: Eurographics Workshop on 3D Object Retrieval. (2008)

  23. Straka, M., Hauswiesner, S., Ruther, M., Bischof, H.: Rapid skin: estimating the 3D human pose and shape in real-time. In: 2012 Second International Conference on 3D Imaging, Modeling, Processing, Visualization and Transmission (3DIMPVT), pp. 41–48. IEEE, New York (2012)

  24. Sumner, R., Popović, J.: Deformation transfer for triangle meshes. In: ACM Transactions on Graphics (TOG), vol. 23, pp. 399–405. ACM, New York (2004)

  25. Xu, K., Li, H., Zhang, H., Cohen-Or, D., Xiong, Y., Cheng, Z.: Style-content separation by anisotropic part scales. In: ACM Transactions on Graphics (TOG), vol. 29, p. 184. ACM, New York (2010)

  26. Ye, M., Wang, X., Yang, R., Ren, L., Pollefeys, M.: Accurate 3d pose estimation from a single depth image. In: IEEE International Conference on Computer Vision (ICCV), 2011, pp. 731–738. IEEE, New York (2011)

  27. Zhang, H., Sheffer, A., Cohen-Or, D., Zhou, Q., Van Kaick, O., Tagliasacchi, A.: Deformation-driven shape correspondence. In: Computer Graphics Forum, vol. 27, pp. 1431–1439. Wiley Online Library, New York (2008)

  28. Zheng, Q., Sharf, A., Tagliasacchi, A., Chen, B., Zhang, H., Sheffer, A., Cohen-Or, D.: Consensus skeleton for non-rigid space-time registration. In: Computer Graphics Forum, vol. 29, pp. 635–644. Wiley Online Library, New York (2010)

  29. Zhou, S., Fu, H., Liu, L., Cohen-Or, D., Han, X.: Parametric reshaping of human bodies in images. ACM Trans. Graph. 29(4), 126 (2010)

    Article  Google Scholar 

Download references

Acknowledgments

This work was partially supported by Grant No. BE2011169, BK2011563 from the Natural Science Foundation of Jiangsu Province and Grant No. 61100111, 61300157, 61201425, 61271231 from the Natural Science Foundation of China.

Author information

Authors and Affiliations

  1. School of Electronic Science and Engineering, Nanjing University, Nanjing, Jiangsu, 210046, China

    Yao Yu, Yu Zhou, Sidan Du, Yuan Jie, Ziqiang Wang & Zhengyu Cai

Authors
  1. Yao Yu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yu Zhou
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Sidan Du
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yuan Jie
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Ziqiang Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Zhengyu Cai
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Yao Yu or Yu Zhou.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Yu, Y., Zhou, Y., Du, S. et al. Learning human shape model from multiple databases with correspondence considering kinematic consensus. Vis Comput 31, 19–33 (2015). https://doi.org/10.1007/s00371-013-0901-6

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00371-013-0901-6

Keywords

Search

Navigation