Coregistration: Simultaneous Alignment and Modeling of Articulated 3D Shape

  • David A. Hirshberg
  • Matthew Loper
  • Eric Rachlin
  • Michael J. Black
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7577)

Abstract

Three-dimensional (3D) shape models are powerful because they enable the inference of object shape from incomplete, noisy, or ambiguous 2D or 3D data. For example, realistic parameterized 3D human body models have been used to infer the shape and pose of people from images. To train such models, a corpus of 3D body scans is typically brought into registration by aligning a common 3D human-shaped template to each scan. This is an ill-posed problem that typically involves solving an optimization problem with regularization terms that penalize implausible deformations of the template. When aligning a corpus, however, we can do better than generic regularization. If we have a model of how the template can deform then alignments can be regularized by this model. Constructing a model of deformations, however, requires having a corpus that is already registered. We address this chicken-and-egg problem by approaching modeling and registration together. By minimizing a single objective function, we reliably obtain high quality registration of noisy, incomplete, laser scans, while simultaneously learning a highly realistic articulated body model. The model greatly improves robustness to noise and missing data. Since the model explains a corpus of body scans, it captures how body shape varies across people and poses.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Hasler, N., Stoll, C., Sunkel, M., Rosenhahn, B., Seidel, H.-P.: A statistical model of human pose and body shape. Comp. Graphics Forum 28(2), 337–346 (2009)CrossRefGoogle Scholar
  2. 2.
    Wuhrer, S., Shu, C., Xi, P.: Landmark-free posture invariant human shape correspondence. The Visual Computer 27, 843–852 (2011)CrossRefGoogle Scholar
  3. 3.
    Allen, B., Curless, B., Popović, Z.: The space of human body shapes: Reconstruction and parameterization from range scans. ACM ToG, 587–594 (2003)Google Scholar
  4. 4.
    Hirshberg, D.A., Loper, M., Rachlin, E., Tsoli, A., Weiss, A., Corner, B., Black, M.J.: Evaluating the automated alignment of 3D human body scans. In: 2nd Int. Conf. 3D Body Scanning Technologies, pp. 76–86 (2011)Google Scholar
  5. 5.
    Xi, P., Lee, W.S., Shu, C.: A data-driven approach to human-body cloning using a segmented body database. In: Proc. 15th Pacific Conf. Comp. Graph. and Apps., pp. 139–147 (2007)Google Scholar
  6. 6.
    Li, H., Adams, B., Guibas, L.J., Pauly, M.: Robust single-view geometry and motion reconstruction. In: ACM SIGGRAPH Asia, vol. 28, pp. 175:1–175:10 (2009)Google Scholar
  7. 7.
    Granger, S., Pennec, X.: Multi-scale EM-ICP: A Fast and Robust Approach for Surface Registration. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002, Part IV. LNCS, vol. 2353, pp. 418–432. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  8. 8.
    Li, H., Sumner, R.W., Pauly, M.: Global correspondence optimization for non-rigid registration of depth scans. Comp. Graphics Forum 27(5), 1421–1430 (2008)CrossRefGoogle Scholar
  9. 9.
    Amberg, B.: Editing Faces in Videos. PhD thesis, University of Basel (2011)Google Scholar
  10. 10.
    Breidt, M., Bülthoff, H.H., Curio, C.: Face models from noisy 3D cameras. In: ACM SIGGRAPH Asia Sketches, pp. 12:1–12:2 (2010)Google Scholar
  11. 11.
    Blanz, V., Vetter, T.: A morphable model for the synthesis of 3D faces. ACM ToG SIGGRAPH, 187–194 (1999)Google Scholar
  12. 12.
    Sorkine, O., Alexa, M.: As-rigid-as-possible surface modeling. In: Proc. 5th Euro. Symp. Geom. Proc., vol. 26, pp. 109–116 (2007)Google Scholar
  13. 13.
    Sumner, R.W., Schmid, J., Pauly, M.: Embedded deformation for shape manipulation. ACM ToG 26(3), 80:1–80:7 (2007)Google Scholar
  14. 14.
    Paysan, P., Knothe, R., Amberg, B., Romdhani, S., Vetter, T.: A 3D face model for pose and illumination invariant face recognition. In: Proc. 6th IEEE Int. Conf. Adv. Video Signal Based Surveillance (AVSS), pp. 296–301 (2009)Google Scholar
  15. 15.
    Anguelov, D., Srinivasan, P., Koller, D., Thrun, S., Rodgers, J., Davis, J.: SCAPE: Shape completion and animation of people. ACM ToG 24, 408–416 (2005)Google Scholar
  16. 16.
    Allen, B., Curless, B., Popović, Z., Hertzmann, A.: Learning a correlated model of identity and pose-dependent body shape variation for real-time synthesis. In: Proc. ACM SIGGRAPH/Eurographics Symp. on Comp. Anim., pp. 147–156 (2006)Google Scholar
  17. 17.
    Sumner, R.W., Popović, J.: Deformation transfer for triangle meshes. ACM ToG 23, 399–405 (2004)Google Scholar
  18. 18.
    Balan, A.: Detailed Human Shape and Pose from Images. PhD thesis, Brown University, Providence, RI (2010)Google Scholar
  19. 19.
    Geman, S., McClure, D.: Statistical methods for tomographic image reconstruction. Bul. Int. Stat. Inst. 52, 5–21 (1987)MathSciNetGoogle Scholar
  20. 20.
    Hirshberg, D.A., Loper, M., Rachlin, E., Black, M.J.: Coregistration: Supplemental material. MPI-IS-TR-004, Max Planck Institute for Intelligent Systems (2012)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • David A. Hirshberg
    • 1
  • Matthew Loper
    • 1
  • Eric Rachlin
    • 1
  • Michael J. Black
    • 1
  1. 1.Max Planck Institute for Intelligent SystemsTübingenGermany

Personalised recommendations