Abstract
We address the problem of automatic recognition of functional parts of man-made 3D shapes in the presence of significant geometric and topological variations. We observe that under such challenging circumstances, the context of a part within a 3D shape provides important cues for learning the semantics of shapes. We propose to model the context as structural relationships between shape parts and use them, in addition to part geometry, as cues for functionality recognition. We represent a 3D shape as a graph interconnecting parts that share some spatial relationships. We model the context of a shape part as walks in the graph. Similarity between shape parts can then be defined as the similarity between their contexts, which in turn can be efficiently computed using graph kernels. This formulation enables us to: (1) find part-wise semantic correspondences between 3D shapes in a nonsupervised manner and without relying on user-specified textual tags, and (2) design classifiers that learn in a supervised manner the functionality of the shape components. We specifically show that the performance of the proposed context-aware similarity measure in finding part-wise correspondences outperforms geometry-only-based techniques and that contextual analysis is effective in dealing with shapes exhibiting large geometric and topological variations.
Supplemental Material
- Aleotti, J. and Caselli, S. 2012. A 3d shape segmentation approach for robot grasping by parts. Robot. Auton. Syst. 60, 3, 358--366. Google ScholarDigital Library
- Attene, M., Robbiano, F., Spagnuolo, M., and Falcidieno, B. 2009. Characterization of 3d shape parts for semantic annotation. Comput.-Aid. Des. 41, 10, 756--763. Google ScholarDigital Library
- Au, O. K.-C., Tai, C.-L., Cohen-Or, D., Zheng, Y., and Fu, H. 2010. Electors voting for fast automatic shape correspondence. Comput. Graph. Forum 29. 645--654.Google Scholar
- Bach, F. R., Thibaux, R., and Jordan, M. I. 2005. Computing regularization paths for learning multiple kernels. In Advances in Neural Information Processing Systems (NIPS'05).Google Scholar
- Bohg, J. and Kragic, D. 2009. Grasping familiar objects using shape context. In International Conference on Advanced Robotics.Google Scholar
- Catalano, C. E., Mortara, M., Spagnuolo, M., and Falcidieno, B. 2011. Semantics and 3d media: Current issues and perspectives. Comput. Graph. 35, 4, 869--877. Google ScholarDigital Library
- Chang, W. and Zwicker, M. 2009. Range scan registration using reduced deformable models. Comput. Graph. Forum 28, 2, 447--456.Google ScholarCross Ref
- Chaudhuri, S., Kalogerakis, E., Guibas, L., and Koltun, V. 2011. Probabilistic reasoning for assembly-based 3d modeling. ACM Trans. Graph. 30, 35:1--35:10. Google ScholarDigital Library
- Chen, X., Golovinskiy, A., and Funkhouser, T. 2009. A benchmark for 3d mesh segmentation. ACM Trans. Graph. 28, 3. Google ScholarDigital Library
- Cos. 2012. The shape coseg dataset. http://web.siat.ac.cn/yunhai/ssl/ssd.htm.Google Scholar
- Fisher, M. and Hanrahan, P. 2010. Context-based search for 3d models. ACM Trans. Graph. 29, 182:1--182:10. Google ScholarDigital Library
- Fisher, M., Savva, M., and Hanrahan, P. 2011. Characterizing structural relationships in scenes using graph kernels. ACM Trans. Graph. 30, 34:1--34:12. Google ScholarDigital Library
- Fu, H., Cohen-Or, D., Dror, G., and Sheffer, A. 2008. Upright orientation of man-made objects. ACM Trans. Graph. 27, 42:1--42:7. Google ScholarDigital Library
- Galleguillos, C. and Belongie, S. J. 2010. Context based object categorization: A critical survey. Comput. Vis. Image Understand. 114, 6, 712--722. Google ScholarDigital Library
- Galleguillos, C., Rabinovich, A., and Belongie, S. 2008. Object categorization using co-occurrence, location and appearance. In IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Google Scholar
- Giorgi, D., Biasotti, S., and Paraboschi, L. 2007. SHREC: Shape retrieval contest: Watertight models track. Tech. rep. http://www.cs.uu.nl/profi/public/SummerSchool/3DRetrieval/USCS07-3dpart6_shrec07.pdf.Google Scholar
- Golovinskiy, A. and Funkhouser, T. A. 2009. Consistent segmentation of 3d models. Comput. Graph. 33, 3, 262--269. Google ScholarDigital Library
- Harchaoui, Z. and Bach, F. 2007. Image classification with segmentation graphs. In IEEE Conference on Computer Vision and Pattern Recognition.Google Scholar
- Huang, Q., Koltun, V., and Guibas, L. 2011. Joint shape segmentation with linear programming. ACM Trans. Graph. 30, 125:1--125:12. Google ScholarDigital Library
- Huang, Q.-X., Adams, B., Wicke, M., and Guibas, L. J. 2008. Nonrigid registration under isometric deformations. In Proceedings of the Symposium on Geometry Processing (SGP'08). Eurographics Association, 1449--1457. Google ScholarDigital Library
- Kalogerakis, E., Hertzmann, A., and Singh, K. 2010. Learning 3d mesh segmentation and labeling. ACM Trans. Graph. 29, 4, 102:1--102:12. Google ScholarDigital Library
- Katz, S. and Tal, A. 2003. Hierarchical mesh decomposition using fuzzy clustering and cuts. ACM Trans. Graph. 22, 3, 954--961. Google ScholarDigital Library
- Kim, V. G., Lipman, Y., and Funkhouser, T. 2011. Blended intrinsic maps. ACM Trans. Graph. 30, 79:1--79:12. Google ScholarDigital Library
- Kyota, F., Watabe, T., Saito, S., and Nakajima, M. 2005. Detection and evaluation of grasping positions for autonomous agents. In Proceedings of the 4th International Conference on Cyberworlds. 453--460. Google ScholarDigital Library
- Laga, H. 2010. Semantics-driven approach for automatic selection of best views of 3d shapes. In Proceedings of the 3rd Eurographics Conference on 3D Object Retrieval (EG3DOR'10). Eurographics Association, 15--22. Google ScholarDigital Library
- Laga, H. 2011. Data-driven approach for automatic orientation of 3d shapes. Vis. Comput. 27, 11, 977--989. Google ScholarDigital Library
- Laga, H., Takahashi, H., and Nakajima, M. 2006. Spherical wavelet descriptors for content-based 3D model retrieval. In Proceedings of the IEEE International Conference on Shape Modeling and Applications. 15. Google ScholarDigital Library
- Li, Y., Wu, X., Chrysathou, Y., Sharf, A., Cohen-Or, D., and Mitra, N. J. 2011. Globfit: Consistently fitting primitives by discovering global relations. ACM Trans. Graph. 30, 4, 52:1--52:12. Google ScholarDigital Library
- Lipman, Y. and Funkhouser, T. 2009. Mobius voting for surface correspondence. ACM Trans. Graph. 28, 72:1--72:12. Google ScholarDigital Library
- Malisiewicz, T. and Efros, A. 2009. Beyond categories: The visual memex model for reasoning about object relationships. In Neural Information Processing Systems. http://repository.cmu.edu/cgi/viewcontent.cgi?article=1784&context=robotics.Google Scholar
- Mitra, N. J., Guibas, L. J., and Pauly, M. 2006. Partial and approximate symmetry detection for 3d geometry. ACM Trans. Graph. 25, 3, 560--568. Google ScholarDigital Library
- Mortara, M., Patane, G., and Spagnuolo, M. 2006. From geometric to semantic human body models. Comput. Graph. 30, 2, 185--196. Google ScholarDigital Library
- Mortara, M., Patane, G., Spagnuolo, M., Falcidieno, B., and Rossignac, J. 2004. Plumber: A method for a multi-scale decomposition of 3d shapes into tubular primitives and bodies. In Proceedings of the 9th ACM Symposium on Solid Modeling and Applications. 339--344. Google ScholarDigital Library
- Oliva, A. and Torralba, A. 2007. The role of context in object recognition. Trends Cogn. Sci. 11, 520--527.Google ScholarCross Ref
- Osada, R., Funkhouser, T. A., Chazelle, B., and Dobkin, D. P. 2002. Shape distributions. ACM Trans. Graph. 21, 807--832. Google ScholarDigital Library
- Ovsjanikov, M., Li, W., Guibas, L., and Mitra, N. J. 2011. Exploration of continuous variability in collections of 3d shapes. ACM Trans. Graph. 30, 33:1--33:10. Google ScholarDigital Library
- Rabinovich, A., Vedaldi, A., Galleguillos, C., Wiewiora, E., and Belongie, S. 2007. Objects in context. In Proceedings of the 11th International Conference on Computer Vision (ICCV'07). 1--8.Google Scholar
- Sahbani, A. and El-Khoury, S. 2009. A hybrid approach for grasping 3d objects. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS'09). IEEE Press, 1272--1277. Google ScholarDigital Library
- Shapira, L., Shalom, S., Shamir, A., Cohen-Or, D., and Zhang, H. 2010. Contextual part analogies in 3d objects. Int. J. Comput. Vis. 89, 1--2, 309--326. Google ScholarDigital Library
- Shapira, L., Shamir, A., and Cohen-Or, D. 2008. Consistent mesh partitioning and skeletonisation using the shape diameter function. Vis. Comput. 24, 249--259. Google ScholarDigital Library
- Shilane, P., Min, P., Kazhda, M., and Funkhouser, T. 2004. The princeton shape benchmark. In Proceedings of the International Conference on Shape Modeling and Applications. 167--178. Google ScholarDigital Library
- Sidi, O., van Kaick, O., Kleiman, Y., Zhang, H., and Cohen-Or, D. 2011. Unsupervised co-segmentation of a set of shapes via descriptorspace clustering. ACM Trans. Graph. 30, 6, 126:1--126:9. Google ScholarDigital Library
- Strat, T. M. and Fischler, M. A. 1991. Context-based vision: Recognizing objects using information from both 2d and 3d imagery. IEEE Trans. Pattern Anal. Mach. Intell. 13, 1050--1065. Google ScholarDigital Library
- van Kaick, O., Tagliasacchi, A., Sidi, O., Zhang, H., Cohen-Or, D., Wolf, L., and Hamarneh, G. 2011. Prior knowledge for shape correspondence. Comput. Graph. Forum 30, 2, 553--562.Google ScholarCross Ref
- van Kaick, O., Zhang, H., Hamarneh, G., and Cohen-Or, D. 2010. A survey on shape correspondence. Comput. Graph. Forum 30, 2, 553--562.Google ScholarCross Ref
- Wang, Y., Xu, K., Li, J., Zhang, H., Shamir, A., Liu, L., Cheng, Z.-Q., and Xiong, Y. 2011. Symmetry hierarchy of man-made objects. Comput. Graph. Forum 30, 2, 287--296.Google ScholarCross Ref
- Zeng, Y., Wang, C., Wang, Y., Gu, X., Samaras, D., and Paragios, N. 2010. Dense non-rigid surface registration using high-order graph matching. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR'10). 382--389.Google Scholar
- Zhang, H., Sheffer, A., Cohen-Or, D., Zhou, Q., van Kaick, O., and Tagliasacchi, A. 2008. Deformation-driven shape correspondence. In Proceedings of the Symposium on Geometry Processing (SGP'08). Eurographics Association, 1431--1439. Google ScholarDigital Library
- Zheng, Y., Cohen-Or, D., and Mitra, N. J. 2013. Smart variations: Functional substructures for part compatibility. Comput. Graph. Forum 32, 2, 133--263.Google ScholarCross Ref
- Zheng, Y., Fu, H., Cohen-Or, D., Au, O. K.-C., and Tai, C.-L. 2011. Component-wise controllers for structure-preserving shape manipulation. Comput. Graph. Forum 30, 2, 563--572.Google ScholarCross Ref
Index Terms
- Geometry and context for semantic correspondences and functionality recognition in man-made 3D shapes
Recommendations
Deformation-driven shape correspondence via shape recognition
Many approaches to shape comparison and recognition start by establishing a shape correspondence. We "turn the table" and show that quality shape correspondences can be obtained by performing many shape recognition tasks. What is more, the method we ...
Deformation-driven topology-varying 3D shape correspondence
We present a deformation-driven approach to topology-varying 3D shape correspondence. In this paradigm, the best correspondence between two shapes is the one that results in a minimal-energy, possibly topology-varying, deformation that transforms one ...
Dissimilarity between two skeletal trees in a context
Skeletal trees are commonly used in order to express geometric properties of the shape. Accordingly, tree-edit distance is used to compute a dissimilarity between two given shapes. We present a new tree-edit based shape matching method which uses a ...
Comments