The Visual Computer

, 27:977

Data-driven approach for automatic orientation of 3D shapes

0riginal Article

Abstract

Visualization and visual browsing of 3D model collections require rendering the 3D models from viewpoints that allow the viewer to distinguish between them. In this paper, we introduce a new framework for the automatic selection of the best views of 3D models. We build on the assumption that models belonging to the same class of shapes share the same salient features that discriminate them from the models of other classes. This allows us to formulate the best-view selection problem as a feature selection and classification task. First a 3D model is described with a set of view-based descriptors characterizing the appearance of the model when it is seen from different viewpoints. In a second step we train a classifier that learns for each shape class the set of 2D views that maximize the intra-class similarity and the inter-class dissimilarities. Finally, we post-process the selected 2D views to estimate their upright orientation. We exploit the fact that most of natural and man-made shapes are symmetric and their upright orientation is aligned with their major axis of symmetry. Experiments on the best-view selection benchmark demonstrate that the estimated best views with our data-driven approach are robust to intra-class variations and are consistent within the models of the same class of shapes. This makes the approach suitable for online visual browsing of large 3D data collections.

Keywords

Best view selection Boosting Shape symmetries 

References

  1. 1.
    Ansary, T.F., Daoudi, M., Vandeborre, J.-P.: A Bayesian 3-d search engine using adaptive views clustering. IEEE Trans. Multimed. 9(1), 78–88 (2007) CrossRefGoogle Scholar
  2. 2.
    Chaouch, M., Verroust-Blondet, A.: Alignment of 3d models. Graph. Models 71, 63–76 (2009) CrossRefGoogle Scholar
  3. 3.
    Chen, D.-Y., Tian, X.-P., Shen, Y.-T., Ouhyoung, M.: On visual similarity based 3D model retrieval. Comput. Graph. Forum 22(3), 223–232 (2003) CrossRefGoogle Scholar
  4. 4.
    Denton, T., Demirci, M.F., Abrahamson, J., Shokoufandeh, A., Dickinson, S.: Selecting canonical views for view-based 3-D object recognition. In: International Conference on Pattern Recognition, vol. 2, pp. 273–276 (2004) Google Scholar
  5. 5.
    Dutagaci, H., Cheung, C.P., Godil, A.: A benchmark for best view selection of 3d objects. In: Proceeding of the ACM Workshop on 3D Object Retrieval, 3DOR2010, pp. 45–50. ACM, New York (2010) CrossRefGoogle Scholar
  6. 6.
    Fu, H., Cohen-Or, D., Dror, G., Sheffer, A.: Upright orientation of man-made objects. In: SIGGRAPH ’08: ACM SIGGRAPH 2008 papers, New York, NY, USA, pp. 1–7. ACM Press, New York (2008) CrossRefGoogle Scholar
  7. 7.
    Karypis, G.: Metis—family of multilevel partitioning algorithms. http://glaros.dtc.umn.edu/gkhome/views/metis (2010)
  8. 8.
    Laga, H.: Semantics-driven approach for automatic selection of best views of 3d shapes. In: 3DOR, pp. 15–22 (2010) Google Scholar
  9. 9.
    Laga, H., Nakajima, M.: Supervised Learning of Salient 2D Views of 3D Models. J. Soc. Art Sci. 7(4), 124–131 (2008) CrossRefGoogle Scholar
  10. 10.
    Lee, C.H., Varshney, A., Jacobs, D.W.: Mesh saliency. In: SIGGRAPH ’05: ACM SIGGRAPH 2005 Papers, pp. 659–666. ACM Press, New York (2005) CrossRefGoogle Scholar
  11. 11.
    Mokhtarian, F., Abbasi, S.: Automatic selection of optimal views in multi-view object recognition. In: The British Machine Vision Conf. (BMVC’00), IEEE Computer Society, 272?281. NDR. National, pp. 272–281 (2000) Google Scholar
  12. 12.
    Mortara, M., Spagnuolo, M.: Semantics-driven best view of 3D shapes. Comput. Graph. 33(3), 280–290 (2009) CrossRefGoogle Scholar
  13. 13.
    Page, D.L., Koschan, A., Sukumar, S.R., Roui-abidi, B., Abidi, M.A.: Shape analysis algorithm based on information theory. In: International Conference on Image Processing, pp. 229–232 (2003) Google Scholar
  14. 14.
    Podolak, J., Shilane, P., Golovinskiy, A., Rusinkiewicz, S., Funkhouser, T.: A planar-reflective symmetry transform for 3D shapes. ACM Trans. Graph., pp. 549–559 (2006) Google Scholar
  15. 15.
    Polonsky, O., Patanè, G., Biasotti, S., Gotsman, C., Spagnuolo, M.: What’s in an image? Vis. Comput. 21(8–10), 840–847 (2005) CrossRefGoogle Scholar
  16. 16.
    Polonsky, O., Patanè, G., Biasotti, S., Gotsman, C., Spagnuolo, M.: What’s in an image? Towards the Computation of the “Best” view of an Object. Vis. Comput. 21(8–10), 840–847 (2005). Proceedings of Pacific Graphics CrossRefGoogle Scholar
  17. 17.
    Shilane, P., Funkhouser, T.: Selecting distinctive 3D shape descriptors for similarity retrieval. In: IEEE International Conference on Shape Modeling and Applications (SMI2006), p. 18 (2006) CrossRefGoogle Scholar
  18. 18.
    Shilane, P., Funkhouser, T.: Distinctive regions of 3D surfaces. ACM Trans. Graph. 26(2), 7 (2007) Google Scholar
  19. 19.
    Shilane, P., Min, P., Kazhdan, M., Funkhouser, T.: The Princeton shape benchmark. In: SMI’04: Proceedings of the Shape Modeling International 2004 (SMI’04), June 2004, pp. 167–178 (2004) CrossRefGoogle Scholar
  20. 20.
    Takahashi, S., Fujishiro, I., Takeshima, Y., Nishita, T.: A feature-driven approach to locating optimal viewpoints for volume visualization. In: IEEE Visualization Conference (VIS2005), p. 63. IEEE Computer Society, Los Alamitos (2005) CrossRefGoogle Scholar
  21. 21.
    Vázquez, P.-P., Feixas, M., Sbert, M., Heidrich, W.: Viewpoint selection using viewpoint entropy. In: Proceedings of the Vision Modeling and Visualization Conference VMV, (2001). ’01, pp. 273–280. Aka GmbH (2001) Google Scholar
  22. 22.
    Vázquez, P.-P., Miquel, F., Sbert, M., Heidrich, W.: Automatic view selection using viewpoint entropy and its applications to image-based modelling. Comput. Graph. Forum 22(4), 689–700 (2003) CrossRefGoogle Scholar
  23. 23.
    Vezhnevet, A.: Gml adaboost matlab toolbox. http://graphics.cs.msu.ru/ru/science/research/machinelearning/adaboosttoolbox, 1 2010
  24. 24.
    Wang, L., Sugiyama, M., Yang, C., Hatano, K., Feng, J.: Theory and algorithm for learning with dissimilarity functions. Neural Comput. 21(5), 1459–1484 (2009) MathSciNetMATHCrossRefGoogle Scholar
  25. 25.
    Yamauchi, H., Saleem, W., Yoshizawa, S., Karni, Z., Belyaev, A., Seidel, H.-P.: Towards stable and salient multi-view representation of 3D shapes. In: Proceedings of the IEEE International Conference on Shape Modeling and Applications 2006 (SMI’06), p. 40 (2006) CrossRefGoogle Scholar

Copyright information

© Springer-Verlag 2011

Authors and Affiliations

  1. 1.Institut TelecomTelecom Lille1 LIFL (UMR8022)LilleFrance

Personalised recommendations