Advertisement

3D Shape Restoration via Matrix Recovery

  • Min Lu
  • Bo Zheng
  • Jun Takamatsu
  • Ko Nishino
  • Katsushi Ikeuchi
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6469)

Abstract

Cultural relics are often damaged and incomplete due to various reasons. For the purpose of helping archaeological studies, we present a novel method for simultaneously restoring the original shapes of a group of similar objects. Based on the assumption that similar shapes are approximately linearly correlated, we use a matrix recovery technique to achieve the restoration. In order to represent input shapes in a matrix form, vectorization of each aligned sample is carried out by stacking coordinates of dense corresponding points that are generated by a surface matching scheme using non-rigid deformation. An experiment using 3D scans of facial sculptures from Bayon is conducted, and the result verifies the feasibility and effectiveness of our method.

Keywords

Null Point Iterative Close Point Moving Little Square Rigid Registration Input Shape 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Kamakura, M., Oishi, T., Takamatsu, J., Ikeuchi, K.: Classification of Bayon faces using 3D models. In: The 11th International Conference on Virtual Systems and Multimedia, VSMM 2005 (2005)Google Scholar
  2. 2.
    Chalmovianský, P., Jüttler, B.: Filling holes in point clouds. In: Wilson, M.J., Martin, R.R. (eds.) Mathematics of Surfaces. LNCS, vol. 2768, pp. 196–212. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  3. 3.
    Ju, T.: Robust repair of polygonal models. ACM Trans. Graph. 23, 888–895 (2004)CrossRefGoogle Scholar
  4. 4.
    Nooruddin, F.S., Turk, G.: Simplification and repair of polygonal models using volumetric techniques. IEEE Transactions on Visualization and Computer Graphics 9, 191–205 (2003)CrossRefGoogle Scholar
  5. 5.
    Sharf, A., Alexa, M., Cohen-Or, D.: Context-based surface completion. In: ACM SIGGRAPH 2004 (2004)Google Scholar
  6. 6.
    Breckon, T.P., Fisher, R.B.: Three-dimensional surface relief completion via nonparametric techniques. IEEE Transactions on Pattern Analysis and Machine Intelligence 30, 2249–2255 (2008)CrossRefGoogle Scholar
  7. 7.
    Pauly, M., Mitra, N.J., Giesen, J., Gross, M., Guibas, L.J.: Example-based 3D scan completion. In: SGP 2005: Proceedings of the Third Eurographics Symposium on Geometry Processing (2005)Google Scholar
  8. 8.
    Kraevoy, V., Sheffer, A.: Template-based mesh completion. In: SGP 2005: Proceedings of the Third Eurographics Symposium on Geometry Processing (2005)Google Scholar
  9. 9.
    Wright, J., Ganesh, A., Rao, S., Peng, Y., Ma, Y.: Robust principal component analysis: Exact recovery of corrupted low-rank matrices via convex optimization. In: Advances in Neural Information Processing Systems 22. MIT Press, Cambridge (2009)Google Scholar
  10. 10.
    Candès, E.J., Li, X., Ma, Y., Wright, J.: Robust principal component analysis? Submitted to Journal of the ACM (2009)Google Scholar
  11. 11.
    Peng, Y., Ganesh, A., Wright, J., Xu, W., Ma, Y.: RASL: Robust alignment by sparse and low-rank decomposition for linearly correlated images. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition, CVPR (2010)Google Scholar
  12. 12.
    Lin, Z., Chen, M., Wu, L., Ma, Y.: The augmented lagrange multiplier method for exact recovery of corrupted low-rank matrices. Submitted to Mathematical Programming (2009)Google Scholar
  13. 13.
    Zhang, H., Sheffer, A., Cohen-Or, D., Zhou, Q., van Kaick, O., Tagliasacchi, A.: Deformation-driven shape correspondence. In: Computer Graphics Forum (Special Issue of Symposium on Geometry Processing 2008), vol. 27, pp. 1431–1439 (2008)Google Scholar
  14. 14.
    Lipman, Y., Funkhouser, T.: Möbius voting for surface correspondence. In: ACM SIGGRAPH 2009 (2009)Google Scholar
  15. 15.
    Zeng, W., Zeng, Y., Wang, Y., Yin, X., Gu, X., Samaras, D.: 3D non-rigid surface matching and registration based on holomorphic differentials. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part III. LNCS, vol. 5304, pp. 1–14. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  16. 16.
    Zeng, Y., Gu, X., Samaras, D., Wang, C., Wang, Y., Paragios, N.: Dense non-rigid surface registration using high-order graph matching. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition, CVPR (2010)Google Scholar
  17. 17.
    Besl, P.J., McKay, N.D.: A method for registration of 3-D shapes. IEEE Transactions on Pattern Analysis and Machine Intelligence 14, 239–256 (1992)CrossRefGoogle Scholar
  18. 18.
    Li, X., Jia, T., Zhang, H.: Expression-insensitive 3D face recognition using sparse representation. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition, CVPR (2009)Google Scholar
  19. 19.
    Alvaro, C., Claudio, E., Antonio, O., Paulo, R.C.: 3D as-rigid-as-possible deformations using MLS. In: The 25th Computer Graphics International Conference, CGI 2007 (2007)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Min Lu
    • 1
  • Bo Zheng
    • 1
  • Jun Takamatsu
    • 2
  • Ko Nishino
    • 3
  • Katsushi Ikeuchi
    • 1
  1. 1.Institute of Industrial ScienceThe University of TokyoTokyoJapan
  2. 2.Nara Institute of Science and TechnologyNaraJapan
  3. 3.Department of Computer ScienceDrexel UniversityPhiladelphiaUSA

Personalised recommendations