Advertisement

Machine Vision and Applications

, Volume 24, Issue 6, pp 1133–1147 | Cite as

Estimating 3D human shapes from measurements

  • Stefanie Wuhrer
  • Chang Shu
Original Paper

Abstract

Recent advances in 3D imaging technologies give rise to databases of human shapes, from which statistical shape models can be built. These statistical models represent prior knowledge of the human shape and enable us to solve shape reconstruction problems from partial information. Generating human shape from traditional anthropometric measurements is such a problem, since these 1D measurements encode 3D shape information. Combined with a statistical shape model, these easy-to-obtain measurements can be leveraged to create 3D human shapes. However, existing methods limit the creation of the shapes to the space spanned by the database and thus require a large amount of training data. In this paper, we introduce a technique that extrapolates the statistically inferred shape to fit the measurement data using non-linear optimization. This method ensures that the generated shape is both human-like and satisfies the measurement conditions. We demonstrate the effectiveness of the method and compare it to existing approaches through extensive experiments, using both synthetic data and real human measurements.

Keywords

Human models Statistical prior  Three-dimensional reconstruction 

Notes

Acknowledgments

We thank the volunteers for participating in the experiment. Furthermore, we thank Pengcheng Xi for helpful discussions and for providing us with the training data, Neil Lawrence for providing us with the SGPLVM code, and the anonymous reviewers for helpful comments. This work has partially been funded by the Cluster of Excellence Multimodal Computing and Interaction within the Excellence Initiative of the German Federal Government.

References

  1. 1.
    Allen, B., Curless, B., Popović, Z.: Proceedings of SIGGRAPH. The space of human body shapes: reconstruction and parameterization from range scans. ACM transactions on graphics, 22(3):587–594, (2003)Google Scholar
  2. 2.
    Allen, B., Curless, B., Popović, Z.: Exploring the space of human body shapes: data-driven synthesis under anthropometric control. In SAE symposium on digital human modeling for design and, engineering, paper \(\#\) 2188, (2004)Google Scholar
  3. 3.
    Anguelov, D., Srinivasan, P., Koller, D., Thrun, S., Rodgers, J., Davis, J.: Proceedings of SIGGRAPH. Scape: shape completion and animation of people. ACM transactions on graphics, 24(3):408–416, (2005)Google Scholar
  4. 4.
    Baek, S.-Y., Lee, K.: Parametric human body shape modeling framework for human-centered product design. Comput-Aided Des. 44(1), 56–67 (2012)CrossRefGoogle Scholar
  5. 5.
    Barber, C.B., Dobkin, D.P., Huhdanpaa, H.: The quickhull algorithm for convex hulls. ACM Trans. Math. Softw. 22(4), 469–483 (1996)MathSciNetzbMATHCrossRefGoogle Scholar
  6. 6.
    Blanz, V., Vetter, T.: In Proceedings of SIGGRAPH, a morphable model for the synthesis of 3d faces. pp. 187–194 (1999)Google Scholar
  7. 7.
    Boisvert, J., Shu, C., Wuhrer, S., Xi, P.: Three-dimensional human shape inference from silhouettes: reconstruction and validation. Mach Vision Appl, 2012Google Scholar
  8. 8.
    Chen, Y., Cipolla, R.: Learning shape priors for single view reconstruction. In workshop on 3D imaging and modelling, pp. 1425–1432 (2009)Google Scholar
  9. 9.
    Chu, C.-H., Tsai, Y.-T., Wang, C.C., Kwok, T.-H.: Exemplar-based statistical model for semantic parametric design of human body. Compt. Ind. 61(6), 541–549 (2010)CrossRefGoogle Scholar
  10. 10.
    DeCarlo, D., Metaxas, D., Stone, M.: In Proceedings of SIGGRAPH, an anthropometric face model using variational techniques. pp. 67–74 (1998)Google Scholar
  11. 11.
    Dijkstra, E.W.: A note on two problems in connexion with graphs. Numerische Mathematik 1(1), 269–271 (1959)MathSciNetzbMATHCrossRefGoogle Scholar
  12. 12.
    Dryden, I., Mardia, K.: Statist. Shape Anal. Wiley, Chichester (2002)Google Scholar
  13. 13.
    Ek, C.H., Torr, P.H.S., Lawrence, N.D.: In Workshop on Machine Learning for Multimodal, Interaction. Gaussian process latent variable models for human pose estimation, pp. 132–143. (2007)Google Scholar
  14. 14.
    Gordon, C.C., Churchill, T., Clauser, C.E., Bradtmiller, B., McConville, J.T., Tebberets, I., Walker, R.A.: Anthropometric survey of US army personnel: methods and summary statistics 1988. Technical report, US Army Natick Research, Development, and Engineering Center, (1989)Google Scholar
  15. 15.
    Guan, P., Weiss, A., Balan, A.O., Black, M.J.: In International Conference on Computer Vision, Estimating human shape and pose from a single image. pp. 1381–1388 (2009)Google Scholar
  16. 16.
    Hasler, N., Ackermann, H., Rosenhahn, B., Thormählen, T., Seidel, H.-P.: In Conference on Computer Vision and, Pattern Recognition. Multilinear pose and body shape estimation of dressed subjects from image sets, pp. 1823–1830. (2010)Google Scholar
  17. 17.
    Hasler, N., Stoll, C., Sunkel, M., Rosenhahn, B., Seidel, H.-P.: A statistical model of human pose and body shape. In: Dutré P., Stamminger M. (eds.) Computer Graphics Forum 28(2), 337–346 (2009)Google Scholar
  18. 18.
    Liu, D.C., Nocedal, J.: On the limited memory method for large scale optimization. Math. Program. 45(3), 503–528 (1989)MathSciNetzbMATHCrossRefGoogle Scholar
  19. 19.
    Robinette, K., Daanen, H., Paquet, E.: In 3-D Digital Imaging and Modeling, the CAESAR project: a 3-D surface anthropometry survey. pp. 180–186, (1999)Google Scholar
  20. 20.
    Schmaltz, C., Rosenhahn, B., Brox, T., Weickert, J.: In machine vision and applications, Region-based pose tracking with occlusions using 3D models. 23(3), 557–577 (2012)Google Scholar
  21. 21.
    Seo, H., Magnenat-Thalmann, N.: An automatic modeling of human bodies from sizing parameters. In Proceedings of the 2003 Symposium on interactive 3D graphics, pp. 19–26, (2003)Google Scholar
  22. 22.
    Seo, H., Yeo, Y.I., Wohn, K.: 3D body reconstruction from photos based on range scan. Technologies for e-learning and digital entertainment, pp. 849–860, (2006)Google Scholar
  23. 23.
    Shon, A.P., Grochow, K., Hertzmann, A., Rao, R.P.N.: Learning shared latent structure for image synthesis and robotic imitation. In neural information processing systems, pp. 1233–1240, (2005) Google Scholar
  24. 24.
    van Kaick, O., Zhang, H., Hamarneh, G., Cohen-Or, D.: A survey on shape correspondence. Compt. Graphics Forum 30(6), 1681–1707 (2011)CrossRefGoogle Scholar
  25. 25.
    Wang, C.C.: Parameterization and parametric design of mannequins. Compt. Aided Des. 37(1), 83–98 (2005)CrossRefGoogle Scholar
  26. 26.
    Wei, W., Luo, X., Li, Z.: Layer-based mannequin reconstruction and parameterization from 3d range data. In advances in geometric modeling and processing, pp. 498–504, (2008)Google Scholar
  27. 27.
    Weiss, A., Hirshberg, D., Black, M.: Home 3D body scans from noisy image and range data. In International Conference on Computer Vision, pp. 1951–1958, (2011)Google Scholar
  28. 28.
    Wuhrer, S., Xi, P., Shu, C.: Human shape correspondence with automatically predicted landmarks. Mach. Vision Appl. 23(4), 821–830 (2012)CrossRefGoogle Scholar
  29. 29.
    Xi, P., Lee, W.-S., Shu, C.: In graphics, interface. Analysis of segmented human body scans, pp. 19–26. (2007)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  1. 1.Saarland University and Max-Planck Institut InformatikSaarbrückenGermany
  2. 2.National Research Council of CanadaOttawaCanada

Personalised recommendations