“Learning part-based templates from large collections of 3D shapes” by Kim, Li, Mitra, Chaudhuri, DiVerdi, et al. …

  • ©Vladimir G. Kim, Wilmot Li, Niloy J. Mitra, Siddhartha Chaudhuri, Stephen DiVerdi, and Thomas (Tom) A. Funkhouser




    Learning part-based templates from large collections of 3D shapes

Session/Category Title: Shape Analysis




    As large repositories of 3D shape collections continue to grow, understanding the data, especially encoding the inter-model similarity and their variations, is of central importance. For example, many data-driven approaches now rely on access to semantic segmentation information, accurate inter-model point-to-point correspondence, and deformation models that characterize the model collections. Existing approaches, however, are either supervised requiring manual labeling; or employ super-linear matching algorithms and thus are unsuited for analyzing large collections spanning many thousands of models. We propose an automatic algorithm that starts with an initial template model and then jointly optimizes for part segmentation, point-to-point surface correspondence, and a compact deformation model to best explain the input model collection. As output, the algorithm produces a set of probabilistic part-based templates that groups the original models into clusters of models capturing their styles and variations. We evaluate our algorithm on several standard datasets and demonstrate its scalability by analyzing much larger collections of up to thousands of shapes.


    1. Amazon, 2012. Amazon mechanical turk, https://www.mturk.com/.Google Scholar
    2. Amit, Y., and Trouve, A. 2007. POP: patchwork of parts models for object recognition. IJCV 75, 2, 267–282. Google ScholarDigital Library
    3. Boykov, Y., Veksler, O., and Zabih, R. 2001. Efficient approximate energy minimization via graph cuts. IEEE transactions on PAMI 20, 12, 1222–1239. Google ScholarDigital Library
    4. Eslami, S. M. A., and Williams, C. 2012. A generative model for parts-based object segmentation. In NIPS.Google Scholar
    5. Felzenszwalb, P. F., and Huttenlocher, D. P. 2005. Pictorial structures for object recognition. IJCV 61, 1, 55–79. Google ScholarDigital Library
    6. Felzenszwalb, P., Girshick, R., McAllester, D., and Ramanan, D. 2010. Object detection with discriminatively trained part-based models. IEEE PAMI 32, 9 (sept.), 1627–1645. Google ScholarDigital Library
    7. Fergus, R., Perona, P., and Zisserman, A. 2003. Object class recognition by unsupervised scale-invariant learning. In IEEE CVPR.Google Scholar
    8. Fisher, M., Savva, M., and Hanrahan, P. 2011. Characterizing structural relationships in scenes using graph kernels. ACM SIGGRAPH 30, 34:1–34:12. Google ScholarDigital Library
    9. Golovinskiy, A., and Funkhouser, T. 2009. Consistent segmentation of 3D models. Proc. SMI 33, 3, 262–269. Google ScholarDigital Library
    10. Gu, C., and Ren, X. 2010. Discriminative mixture-of-templates for viewpoint classification. In ECCV. Google ScholarDigital Library
    11. Hu, R., Fan, L., and Liu, L. 2012. Co-segmentation of 3d shapes via subspace clustering. Computer Graphics Forum (Proc. SGP) 31, 5, 1703–1713. Google ScholarDigital Library
    12. Huang, Q., Koltun, V., and Guibas, L. 2011. Joint shape segmentation with linear programming. In ACM SIGGRAPH Asia, 125:1–125:12. Google ScholarDigital Library
    13. Huang, Q.-x., Zhang, G.-X., Gao, L., Hu, S.-M., Butscher, A., and Guibas, L. 2012. An optimization approach for extracting and encoding consistent maps. SIGGRAPH Asia. Google ScholarDigital Library
    14. Jain, A., Zhong, Y., and Dubuisson-Jolly, M.-P. 1998. Deformable template models: A review. Signal Processing 71, 2, 109–129. Google ScholarDigital Library
    15. Kalogerakis, E., Hertzmann, A., and Singh, K. 2010. Learning 3D mesh segmentation and labeling. In ACM SIGGRAPH, 102:1–102:12. Google ScholarDigital Library
    16. Kalogerakis, E., Chaudhuri, S., Koller, D., and Koltun, V. 2012. A probabilistic model for component-based shape synthesis. SIGGRAPH. Google ScholarDigital Library
    17. Katz, S., and Tal, A. 2003. Hierarchical mesh decomposition using fuzzy clustering and cuts. ACM Trans. Graph. 22, 3, 954–961. Google ScholarDigital Library
    18. Kim, V. G., Li, W., Mitra, N., DiVerdi, S., and Funkhouser, T. 2012. Exploring collections of 3D models using fuzzy correspondences. Trans. on Graphis (Proc. of SIGGRAPH). Google ScholarDigital Library
    19. Kim, Y. M., Mitra, N. J., Yan, D., and Guibas, L. 2012. Acquiring 3d indoor environments with variability and repetition. SIGGRAPH Asia. Google ScholarDigital Library
    20. Lopez-Sastre, R., Tuytelaars, T., and Savarese, S. 2011. Deformable part models revisited: A performance evaluation for object category pose estimation. In ICCV Workshop on Challenges and Opportunities in Robot Perception.Google Scholar
    21. Nan, L., Xie, K., and Sharf, A. 2012. A search-classify approach for cluttered indoor scene understanding. ACM Trans. Graph. (Proc. SIGGRAPH Asia) 31, 6. Google ScholarDigital Library
    22. Nguyen, A., Ben-Chen, M., Welnicka, K., Ye, Y., and Guibas, L. 2011. An optimization approach to improving collections of shape maps. SGP 30, 5, 1481–1491.Google Scholar
    23. Ovsjanikov, M., Li, W., Guibas, L., and Mitra, N. J. 2011. Exploration of continuous variability in collections of 3D shapes. ACM SIGGRAPH 30, 4, 33:1–33:10. Google ScholarDigital Library
    24. Shapira, L., Shalom, S., Shamir, A., Cohen-Or, D., and Zhang, H. 2010. Contextual part analogies in 3d objects. IJCV 89, 2-3, 309–326. Google ScholarDigital Library
    25. Shen, C.-H., Fu, H., Chen, K., and Hu, S.-M. 2012. Structure recovery by part assembly. SIGGRAPH Asia. Google ScholarDigital Library
    26. Sidi, O., van Kaick, O., Kleiman, Y., Zhang, H., and Cohen-Or, D. 2011. Unsupervised co-segmentation of a set of shapes via descriptor-space spectral clustering. ACM SIGGRAPH Asia 30, 6, 126:1–126:9. Google ScholarDigital Library
    27. Sorkine, O., 2007. Least-squares rigid motion using svd, http://igl.ethz.ch/projects/ARAP/svd_rot.pdf.Google Scholar
    28. Trimble, 2012. Trimble 3D warehouse, http://sketchup.google.com/3dwarehouse/.Google Scholar
    29. van Kaick, O., Tagliasacchi, A., Sidi, O., Zhang, H., Cohen-Or, D., Wolf, L., and Hamarneh, G. 2011. Prior knowledge for part correspondence. CGF Eurographics 30, 2, 553–562.Google ScholarCross Ref
    30. van Kaick, O., Zhang, H., Hamarneh, G., and Cohen-Or, D. 2011. A survey on shape correspondence. CGF 30, 6, 1681–1707.Google ScholarCross Ref
    31. Wang, Y., Asafi, S., van Kaick, O., Zhang, H., Cohen-Or, D., and Chenand, B. 2012. Active co-analysis of a set of shapes. SIGGRAPH Asia. Google ScholarDigital Library
    32. Weber, M., Welling, M., and Perona, P. 2000. Towards automatic discovery of object categories. In IEEE CVPR.Google Scholar
    33. Weber, M., Welling, M., and Perona, P. 2000. Unsupervised learning of models for recognition. In ECCV. Google ScholarDigital Library
    34. Xu, K., Li, H., Zhang, H., Daniel Cohen-Or, Y. X., and Cheng, Z.-Q. 2010. Style-content separation by anisotropic part scales. SIGGRAPH Asia. Google ScholarDigital Library
    35. Xu, K., Zhang, H., Cohen-Or, D., and Chen, B. 2012. Fit and diverse: Set evolution for inspiring 3D shape galleries. ACM Trans. on Graph (Proc. of SIGGRAPH) 31. Google ScholarDigital Library
    36. Zheng, Y., Cohen-Or, D., and Mitra, N. J. 2013. Smart variations: Functional substructures for part compatibility. CGF Eurographics.Google Scholar

ACM Digital Library Publication: