Abstract
Acquiring 3D geometry of an object is a tedious and time-consuming task, typically requiring scanning the surface from multiple viewpoints. In this work we focus on reconstructing complete geometry from a single scan acquired with a low-quality consumer-level scanning device. Our method uses a collection of example 3D shapes to build structural part-based priors that are necessary to complete the shape. In our representation, we associate a local coordinate system to each part and learn the distribution of positions and orientations of all the other parts from the database, which implicitly also defines positions of symmetry planes and symmetry axes. At the inference stage, this knowledge enables us to analyze incomplete point clouds with substantial occlusions, because observing only a few regions is still sufficient to infer the global structure. Once the parts and the symmetries are estimated, both data sources, symmetry and database, are fused to complete the point cloud. We evaluate our technique on a synthetic dataset containing 481 shapes, and on real scans acquired with a Kinect scanner. Our method demonstrates high accuracy for the estimated part structure and detected symmetries, enabling higher quality shape completions in comparison to alternative techniques.
- Breiman, L. 2001. Random forests. Machine Learning 45, 1, 5--32. Google ScholarDigital Library
- Chaudhuri, S., Kalogerakis, E., Guibas, L., and Koltun, V. 2011. Probabilistic reasoning for assembly-based 3d modeling. ACM TOG 30, 4 (July), 35:1--35:10. Google ScholarDigital Library
- Choi, S., Zhou, Q.-Y., and Koltun, V. 2015. Robust reconstruction of indoor scenes. CVPR.Google Scholar
- Eiter, T., and Mannila, H. 1997. Distance measures for point sets and their computation. Acta Informatica 34, 2, 109--133.Google ScholarCross Ref
- Felzenszwalb, P., McAllester, D., and Ramanan, D. 2008. A discriminatively trained, multiscale, deformable part model. In IEEE CVPR, 1--8.Google Scholar
- Fish, N., Averkiou, M., van Kaick, O., Sorkine-Hornung, O., Cohen-Or, D., and Mitra, N. J. 2014. Meta-representation of shape families. ACM TOG 33, 4, 34:1--34:11. Google ScholarDigital Library
- Golovinskiy, A., and Funkhouser, T. 2009. Consistent segmentation of 3D models. Proc. SMI 33, 3, 262--269. Google ScholarDigital Library
- Han, F., and Zhu, S.-C. 2009. Bottom-up/top-down image parsing with attribute grammar. IEEE PAMI 31, 1, 59--73. Google ScholarDigital Library
- Hu, R., Fan, L., and Liu, L. 2012. Co-segmentation of 3d shapes via subspace clustering. SGP 31, 5, 1703--1713. Google ScholarDigital Library
- Huang, Q., Koltun, V., and Guibas, L. 2011. Joint shape segmentation with linear programming. In SIGGRAPH Asia. Google ScholarDigital Library
- Huang, Q., Wang, F., and Guibas, L. 2014. Functional map networks for analyzing and exploring large shape collections. ACM TOG 33, 4 (July), 36:1--36:11. Google ScholarDigital Library
- Janoch, A., Karayev, S., Jia, Y., Barron, J., Fritz, M., Saenko, K., and Darrell, T. 2011. A category-level 3-d object dataset: Putting the kinect to work. In ICCV Workshop on Consumer Depth Cameras in Computer Vision, 1168--1174.Google Scholar
- Kalogerakis, E., Hertzmann, A., and Singh, K. 2010. Learning 3D mesh segmentation and labeling. In SIGGRAPH, 102:1--102:12. Google ScholarDigital Library
- Kalogerakis, E., Chaudhuri, S., Koller, D., and Koltun, V. 2012. A probabilistic model for component-based shape synthesis. ACM TOG 31, 4 (July), 55:1--55:11. Google ScholarDigital Library
- Kazhdan, M., and Hoppe, H. 2013. Screened poisson surface reconstruction. Transactions on Graphics 32, 3. Google ScholarDigital Library
- Kim, Y. M., Mitra, N. J., Yan, D.-M., and Guibas, L. 2012. Acquiring 3d indoor environments with variability and repetition. ACM TOG 31, 6 (Nov.), 138:1--138:11. Google ScholarDigital Library
- Kim, V. G., Li, W., Mitra, N. J., Chaudhuri, S., DiVerdi, S., and Funkhouser, T. 2013. Learning part-based templates from large collections of 3d shapes. ACM TOG 32, 4, 70:1--70:12. Google ScholarDigital Library
- Kim, Y. M., Mitra, N. J., Huang, Q., and Guibas, L. 2013. Guided real-time scanning of indoor objects. Computer Graphics Forum 32, 7, 177--186.Google ScholarCross Ref
- Kim, V. G., Chaudhuri, S., Guibas, L., and Funkhouser, T. 2014. Shape2pose: Human-centric shape analysis. ACM TOG 33, 4 (July), 120:1--120:12. Google ScholarDigital Library
- Kolmogorov, V. 2006. Convergent tree-reweighted message passing for energy minimization. IEEE PAMI 28, 10, 1568--1583. Google ScholarDigital Library
- Lai, K., Bo, L., Ren, X., and Fox, D. 2011. A large-scale hierarchical multi-view rgb-d object dataset. In IEEE ICRA, 1817--1824.Google Scholar
- Li, Y., Dai, A., Guibas, L., and Niessner, M. 2015. Database-assisted object retrieval for real-time 3d reconstruction. Eurographics. Google ScholarDigital Library
- Liu, T., Chaudhuri, S., Kim, V. G., Huang, Q., Mitra, N. J., and Funkhouser, T. 2014. Creating consistent scene graphs using a probabilistic grammar. ACM TOG 33, 6, 211:1--211:12. Google ScholarDigital Library
- Makadia, A., and Yumer, M. E. 2014. Learning 3d part detection from sparsely labeled data. In 3DV, IEEE. Google ScholarDigital Library
- Martinovic, A., and Van Gool, L. 2013. Bayesian grammar learning for inverse procedural modeling. In IEEE CVPR, 201--208. Google ScholarDigital Library
- Mitra, N. J., Guibas, L., and Pauly, M. 2006. Partial and approximate symmetry detection for 3d geometry. SIGGRAPH. Google ScholarDigital Library
- Mitra, N. J., Pauly, M., Wand, M., and Ceylan, D. 2013. Symmetry in 3d geometry: Extraction and applications. CGF. Google ScholarDigital Library
- Nan, L., Xie, K., and Sharf, A. 2012. A search-classify approach for cluttered indoor scene understanding. SIGGRAPH Asia 31, 6. Google ScholarDigital Library
- Pauly, M., Mitra, N. J., Giesen, J., Gross, M., and Guibas, L. 2005. Example-based 3d scan completion. SGP. Google ScholarDigital Library
- Pauly, M., Mitra, N. J., wallner, J., Pottmann, H., and Guibas, L. J. 2008. Discovering structural regularity in 3d geometry. ACM TOG 27, 3 (Aug.), 43:1--43:11. Google ScholarDigital Library
- Podolak, J., Shilane, P., Golovinskiy, A., Rusinkiewicz, S., and Funkhouser, T. 2006. A planar-reflective symmetry transform for 3D shapes. ACM TOG 25, 3. Google ScholarDigital Library
- Shao, T., Monszpart, A., Zheng, Y., Koo, B., Xu, W., Zhou, K., and Mitra, N. J. 2014. Imagining the unseen: Stability-based cuboid arrangements for scene understanding. ACM TOG 33, 6 (Nov.), 209:1--209:11. Google ScholarDigital Library
- Shen, C.-H., Fu, H., Chen, K., and Hu, S.-M. 2012. Structure recovery by part assembly. ACM TOG 31, 6 (Nov.), 180:1--180:11. 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 descriptor-space spectral clustering. SIGGRAPH Asia 30, 6, 126:1--126:9. Google ScholarDigital Library
- Silberman, N., Hoiem, D., Kohli, P., and Fergus, R. 2012. Indoor segmentation and support inference from rgbd images. In ECCV, 746--760. Google ScholarDigital Library
- Sipiran, I., Gregor, R., and Schreck, T. 2014. Approximate symmetry detection in partial 3d meshes. CGF 33, 7, 131--140. Google ScholarDigital Library
- Thrun, S., and Wegbreit, B. 2005. Shape from symmetry. In ICCV, 1824--1831. Google ScholarDigital Library
- Wächter, A., and Biegler, L. T. 2006. On the implementation of an interior-point filter line-search algorithm for large-scale nonlinear programming. Mathematical Programming 106, 1. Google ScholarDigital Library
- Wang, Y., Asafi, S., van Kaick, O., Zhang, H., Cohen-Or, D., and Chen, B. 2012. Active co-analysis of a set of shapes. ACM TOG 31, 6 (Nov.), 165:1--165:10. Google ScholarDigital Library
- Wu, C., Lenz, I., and Saxena, A. 2014. Hierarchical semantic labeling for task-relevant rgb-d perception. RSS.Google Scholar
- Xie, Z., Xu, K., Liu, L., and Xiong, Y. 2014. 3d shape segmentation and labeling via extreme learning machine. SGP.Google Scholar
- Xu, K., Li, H., Zhang, H., Cohen-Or, D., Xiong, Y., and Cheng, Z. 2010. Style-content separation by anisotropic part scales. SIGGRAPH Asia 29, 5. Google ScholarDigital Library
- Xu, K., Zhang, H., Cohen-Or, D., and Chen, B. 2012. Fit and diverse: Set evolution for inspiring 3d shape galleries. 57:1--57:10.Google Scholar
- Yumer, M. E., and Kara, L. B. 2014. Co-constrained handles for deformation in shape collections. ACM TOG 33, 6. Google ScholarDigital Library
- Yumer, M., Chun, W., and Makadia, A. 2014. Co-segmentation of textured 3d shapes with sparse annotations. In IEEE CVPR, 240--247. Google ScholarDigital Library
- Zheng, Q., Sharf, A., Wan, G., Li, Y., Mitra, N. J., Cohen-Or, D., and Chen, B. 2010. Non-local scan consolidation for 3d urban scenes. ACM TOG 29, 4 (July), 94:1--94:9. Google ScholarDigital Library
- Zheng, Y., Cohen-Or, D., and Mitra, N. J. 2013. Smart variations: Functional substructures for part compatibility. Computer Graphics Forum 32, 195--204.Google ScholarCross Ref
Index Terms
- Data-driven structural priors for shape completion
Recommendations
Learning Shape Priors for Single-View 3D Completion And Reconstruction
Computer Vision – ECCV 2018AbstractThe problem of single-view 3D shape completion or reconstruction is challenging, because among the many possible shapes that explain an observation, most are implausible and do not correspond to natural objects. Recent research in the field has ...
Relation-based parametrization and exploration of shape collections
We present a parametrization of shape collections based on relations between parts.The way in which the shapes vary is captured automatically.Exploration allows intuitive browsing or searching for more specific shapes.A visualization aids the user in ...
Non-rigid Registration with Reliable Distance Field for Dynamic Shape Completion
3DV '14: Proceedings of the 2014 Second International Conference on 3D Vision - Volume 02We propose a non-rigid registration method for completion of dynamic shapes with occlusion. Our method is based on the idea that an occluded region in a certain frame should be visible in another frame and that local regions should be moving rigidly ...
Comments