Abstract
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 develop computes a fine-grained, topology-varying part correspondence between two 3D shapes where the core evaluation mechanism only recognizes shapes globally. This is made possible by casting the part correspondence problem in a deformation-driven framework and relying on a data-driven "deformation energy" which rates visual similarity between deformed shapes and models from a shape repository. Our basic premise is that if a correspondence between two chairs (or airplanes, bicycles, etc.) is correct, then a reasonable deformation between the two chairs anchored on the correspondence ought to produce plausible, "chair-like" in-between shapes.
Given two 3D shapes belonging to the same category, we perform a top-down, hierarchical search for part correspondences. For a candidate correspondence at each level of the search hierarchy, we deform one input shape into the other, while respecting the correspondence, and rate the correspondence based on how well the resulting deformed shapes resemble other shapes from ShapeNet belonging to the same category as the inputs. The resemblance, i.e., plausibility, is measured by comparing multi-view depth images over category-specific features learned for the various shape categories. We demonstrate clear improvements over state-of-the-art approaches through tests covering extensive sets of man-made models with rich geometric and topological variations.
Supplemental Material
- Ibraheem Alhashim, Honghua Li, Kai Xu, Junjie Cao, Rui Ma, and Hao Zhang. 2014. Topology-Varying 3D Shape Creation via Structural Blending. ACM Trans. on Graphics 33, 4 (2014), 158:1--158:10.Google ScholarDigital Library
- Ibraheem Alhashim, Kai Xu, Yixin Zhuang, Junjie Cao, Patricio Simari, and Hao Zhang. 2015. Deformation-driven Topology-varying 3D Shape Correspondence. ACM Trans. on Graphics 34, 6 (2015), 236:1--236:13.Google ScholarDigital Library
- Brett Allen, Brian Curless, and Zoran Popović. 2003. The Space of Human Body Shapes: Reconstruction and Parameterization from Range Scans. ACM Trans. on Graphics 22, 3 (2003), 587--594. Google ScholarDigital Library
- Aayush Bansal, Abhinav Shrivastava, Carl Doersch, and Abhinav Gupta. 2015. Mid-level elements for object detection. arXiv preprint arXiv:1504.07284 (2015).Google Scholar
- Volker Blanz and Thomas Vetter. 1999. A morphable model for the synthesis of 3D faces. In Proc. SIGGRAPH. 187--194. Google ScholarDigital Library
- Ding-Yun Chen, Xiao-Pei Tian, Yu-Te Shen, and Ming Ouhyoung. 2003. On visual similarity based 3D model retrieval. Computer Graphics Forum (Proc. EUROGRAPHICS) 22, 3 (2003), 223--232.Google ScholarCross Ref
- Navneet Dalal and Bill Triggs. 2005. Histograms of oriented gradients for human detection. In Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on, Vol. 1. IEEE, 886--893. Google ScholarDigital Library
- Noa Fish, van Kaick, Amit Bermano, and Daniel Cohen-Or. 2016. Structure-oriented Networks of Shape Collections. ACM Trans. on Graphics 35, 6 (2016), 171:1--171:14.Google ScholarDigital Library
- Lin Gao, Yu-Kun Lai, Qixing Huang, and Shi-Min Hu. 2013. A Data-Driven Approach to Realistic Shape Morphing. Computer Graphics Forum 32, 2 (2013), 449--457. Google ScholarCross Ref
- Aleksey Golovinskiy and Thomas Funkhouser. 2009. Consistent segmentation of 3D models. Computers & Graphics (Proc. SMI) 33, 3 (2009), 262--269.Google ScholarDigital Library
- Ruizhen Hu, Oliver van Kaick, Bojian Wu, Hui Huang, Ariel Shamir, and Hao Zhang. 2016. Learning How Objects Function via Co-Analysis of Interactions. ACM Trans. on Graphics 35, 4 (2016), 47:1--47:13.Google ScholarDigital Library
- Qixing Huang, Vladlen Koltun, and Leonidas Guibas. 2011. Joint shape segmentation with linear programming. ACM Trans. on Graphics 30, 6 (2011), 125:1--125:12.Google ScholarDigital Library
- Qixing Huang, Fan Wang, and Leonidas Guibas. 2014. Functional map networks for analyzing and exploring large shape collections. ACM Trans. on Graphics 33, 4 (2014), 36.Google ScholarDigital Library
- Qi-Xing Huang, Hao Su, and Leonidas Guibas. 2013. Fine-grained Semi-supervised Labeling of Large Shape Collections. ACM Trans. on Graphics 32, 6 (2013), 190:1--190:10.Google ScholarDigital Library
- Michael Kazhdan, Thomas Funkhouser, and Szymon Rusinkiewicz. 2004. Symmetry descriptors and 3D shape matching. In Proceedings of the 2004 Eurographics/ACM SIGGRAPH symposium on Geometry processing. 115--123.Google ScholarDigital Library
- Vladimir G. Kim, Wilmot Li, Niloy J. Mitra, Siddhartha Chaudhuri, Stephen DiVerdi, and Thomas Funkhouser. 2013. Learning Part-based Templates from Large Collections of 3D Shapes. ACM Trans. on Graphics 32, 4 (2013), 70:1--70:12.Google ScholarDigital Library
- Yanir Kleiman, Oliver van Kaick, Olga Sorkine-Hornung, and Daniel Cohen-Or. 2015. SHED: Shape Edit Distance for Fine-grained Shape Similarity. ACM Trans. on Graphics 34, 6 (2015), 235:1--235:11.Google ScholarDigital Library
- Hamid Laga, Michela Mortara, and Michela Spagnuolo. 2013. Geometry and Context for Semantic Correspondences and Functionality Recognition in Man-made 3D Shapes. ACM Trans. on Graphics 32, 5 (2013), 150:1--150:16.Google ScholarDigital Library
- Jonathan Masci, Davide Boscaini, Michael Bronstein, and Pierre Vandergheynst. 2015. Geodesic convolutional neural networks on Riemannian manifolds. In Proc. of ICCV Workshops. 37--45. Google ScholarDigital Library
- Niloy Mitra, Michael Wand, Hao (Richard) Zhang, Daniel Cohen-Or, Vladimir Kim, and Qi-Xing Huang. 2013. Structure-aware Shape Processing. In SIGGRAPH Asia 2013 Courses. 1:1--1:20.Google Scholar
- Alain Pitiot, Herve Delingette, and Paul Thompson. 2007. Learning Shape Correspondence for n-D curves. Int. J. Computer Vision. 71, 1 (2007), 71--88. Google ScholarDigital Library
- Joshua Podolak, Philip Shilane, Aleksey Golovinskiy, Szymon Rusinkiewicz, and Thomas Funkhouser. 2006. A planar-reflective symmetry transform for 3D shapes. ACM Trans. on Graphics 25, 3 (2006), 549--559. Google ScholarDigital Library
- Charles Qi, Hao Su, Matthias Niessner, Angela Dai, Mengyuan Yan, and Leonidas Guibas. 2016. Volumetric and Multi-View CNNs for Object Classification on 3D Data. In Proc. IEEE Conf. on CVPR. 5648--5656.Google ScholarCross Ref
- Emanuele Rodolà, Samuel Rota Bulo, Thomas Windheuser, Matthias Vestner, and Daniel Cremers. 2014. Dense non-rigid shape correspondence using random forests. In Proc. IEEE Conf. on CVPR. 4177--4184. Google ScholarDigital Library
- T. W. Sederberg and E. Greenwood. 1992. A physically based approach to 2-D shape blending. In Proc. SIGGRAPH. 25--34. Google ScholarDigital Library
- Oana Sidi, Oliver van Kaick, Yanir Kleiman, Hao Zhang, and Daniel Cohen-Or. 2011. Unsupervised Co-Segmentation of a Set of Shapes via Descriptor-Space Spectral Clustering. ACM Trans. on Graphics 30, 6 (2011), 126:1--126:9.Google ScholarDigital Library
- Saurabh Singh, Abhinav Gupta, and Alexei Efros. 2012. Unsupervised discovery of mid-level discriminative patches. In Proc. Euro. Conf. on Comp. Vis. (ECCV). 73--86. Google ScholarDigital Library
- Hao Su, Manolis Savva, Li Yi, Angel X. Chang, Shuran Song, Fisher Yu, Zimo Li, Jianxiong Xiao, Qixing Huang, Silvio Savarese, Thomas Funkhouser, Patrick Hanrahan, and Leonidas J. Guibas. 2015. ShapeNet: An Information-Rich 3D Model Repository.Google Scholar
- Art Tevs, Qixing Huang, Michael Wand, Hans-Peter Seidel, and Leonidas Guibas. 2014. Relating Shapes via Geometric Symmetries and Regularities. ACM Trans. on Graphics 33, 4 (2014), 119:1--119:12.Google ScholarDigital Library
- Jasper RR Uijlings, Koen EA van de Sande, Theo Gevers, and Arnold WM Smeulders. 2013. Selective search for object recognition. Int. J. Computer Vision. 104, 2 (2013), 154--171.Google ScholarDigital Library
- Oliver van Kaick, Noa Fish, Yanir Kleiman, Shmuel Asafi, and Daniel Cohen-Or. 2014. Shape Segmentation by Approximate Convexity Analysis. ACM Trans. on Graphics 34, 1 (2014), 4:1--4:11.Google Scholar
- Oliver van Kaick, Andrea Tagliasacchi, Oana Sidi, Hao Zhang, Daniel Cohen-Or, Lior Wolf, and Ghassan Hamarneh. 2011. Prior Knowledge for Shape Correspondence. Computer Graphics Forum 30, 2 (2011), 553--562. Google ScholarCross Ref
- Oliver van Kaick, Kai Xu, Hao Zhang, Yanzhen Wang, Shuyang Sun, Ariel Shamir, and Daniel Cohen-Or. 2013. Co-Hierarchical Analysis of Shape Structures. ACM Trans. on Graphics 32, 4 (2013), 69:1--69:10.Google ScholarDigital Library
- Oliver van Kaick, Hao Zhang, Ghassan Hamarneh, and Daniel Cohen-Or. 2010. A Survey on Shape Correspondence. Computer Graphics Forum 30, 6 (2010), 1681--1707. Google ScholarCross Ref
- Yanzhen Wang, Kai Xu, Jun Li, Hao Zhang, Ariel Shamir, Ligang Liu, Zhiquan Cheng, and Yueshan Xiong. 2011. Symmetry Hierarchy of Man-Made Objects. Computer Graphics Forum 30, 2 (2011), 287--296. Google ScholarCross Ref
- Kai Xu, Vladimir Kim, Qixing Huang, and Evangelos Kalogerakis. 2016. Data-Driven Shape Analysis and Processing. Computer Graphics Forum (2016), to appear. Google ScholarDigital Library
- Kai Xu, Honghua Li, Hao Zhang, Daniel Cohen-Or, Yueshan Xiong, and Zhiquan Cheng. 2010. Style-Content Separation by Anisotropic Part Scales. ACM Trans. on Graphics 29, 6 (2010), 184:1--184:9.Google ScholarDigital Library
- Kai Xu, Hao Zhang, Daniel Cohen-Or, and Baoquan Chen. 2012. Fit and Diverse: Set Evolution for Inspiring 3D Shape Galleries. ACM Trans. on Graphics 31, 4 (2012), 57:1--10.Google ScholarDigital Library
- Lihi Zelnik-Manor and Pietro Perona. 2004. Self-tuning spectral clustering. In NIPS. 1601--1608.Google Scholar
- Hao Zhang, Alla Sheffer, Daniel Cohen-Or, Qingnan Zhou, Oliver van Kaick, and Andrea Tagliasacchi. 2008. Deformation-Driven Shape Correspondence. Computer Graphics Forum (Proc. SGP) 27, 5 (2008), 1431--1439.Google ScholarDigital Library
- Youyi Zheng, Daniel Cohen-Or, Melinos Averkiou, and Niloy J. Mitra. 2014. Recurring Part Arrangements in Shape Collections. Computer Graphics Forum 33, 2 (2014), 115--124. Google ScholarDigital Library
Index Terms
- Deformation-driven shape correspondence via shape recognition
Recommendations
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 ...
Hierarchical Spherical Deformation for Shape Correspondence
Medical Image Computing and Computer Assisted Intervention – MICCAI 2018AbstractWe present novel spherical deformation for a landmark-free shape correspondence in a group-wise manner. In this work, we aim at both addressing template selection bias and minimizing registration distortion in a single framework. The proposed ...
Medial-axis-driven shape deformation with volume preservation
The medial axis is a natural skeleton for shapes. However, it is rarely used in the existing skeleton-based shape deformation techniques. In this paper, we propose a novel medial-axis-driven skin surface deformation algorithm with volume preservation ...
Comments