Abstract
Assembly-based methods make 3D shape modelling convenient and effective even for non-expert users. However, it is still difficult to choose a reasonable component from an unlabeled shape dataset. In this work, the spectral graph convolutional neural networks (graph CNNs) are used to label a subcomponent in the given shape by their context information and geometry features using convolution operation. Then an appropriate component to replace the above labeled component is found by the same network according to their labels from shapes database. After replacing the component, reasonable results can be obtained in most experiments, which prove the reliability of our method. In addition, we found that the use of dropout and residual could greatly improve the training and performance. The context information, compared with the geometry features, is more effective in creating new shapes.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Kalogerakis, E., Chaudhuri, S., Koller, D., et al.: A probabilistic model for component-based shape synthesis. ACM Trans. Graph. (TOG) 31(4), 55 (2012)
Su, X., Chen, X., Fu, Q., et al.: Cross-class 3D object synthesis guided by reference examples. Comput. Graph. 54, 145–153 (2016)
Zheng, Y., Cohen-Or, D., Mitra, N.J.: Smart variations: functional substructures for part compatibility. Comput. Graph. Forum 32(2pt2), 195–204 (2013)
Funkhouser, T., Kazhdan, M., Shilane, P., et al.: Modeling by example. ACM Trans. Graph. (TOG) 23(3), 652–663 (2004)
Shen, C.H., Fu, H., Chen, K., et al.: Structure recovery by part assembly. ACM Trans. Graph. (TOG) 31(6), 180 (2012)
Jaiswal, P., Huang, J., Rai, R.: Assembly-based conceptual 3D modeling with unlabeled components using probabilistic factor graph. Comput. Aided Des. 74, 45–54 (2016)
Xu, K., Kim, V.G., Huang, Q. et al.: Data-driven shape analysis and processing. SIGGRAPH ASIA 2016 Courses, p. 4. ACM (2016)
Sung, M., Su, H., Kim, V.G., et al.: Complementme: weakly-supervised component suggestions for 3D modeling. ACM Trans. Graph. (TOG) 36(6), 226 (2017)
Qi, C.R., Su, H., Mo, K., et al.: Pointnet: deep learning on point sets for 3D classification and segmentation. Proc. CVPR IEEE 1(2), 4 (2017)
Wu, Z., Song, S., Khosla, A. et al.: 3D shapenets: a deep representation for volumetric shapes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1912–1920 (2015)
Bruna, J., Zaremba, W., Szlam, A., LeCun, Y.: Spectral networks and locally connected networks on graphs (2013). arXiv preprint arXiv:1312.6203
Defferrard, M., Bresson, X., Vandergheynst, P.: Convolutional neural networks on graphs with fast localized spectral filtering. Adv. Neural Inf. Process. Syst. 29, 3844–3852 (2016)
Shuman, D.I., Narang, S.K., Frossard, P., et al.: The emerging field of signal processing on graphs: extending high-dimensional data analysis to networks and other irregular domains. IEEE Signal Process. Mag. 30(3), 83–98 (2013)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks (2016). arXiv preprint arXiv:1609.02907
Princeton ModelNet. http://modelnet.cs.princeton.edu/. Accessed 21 May 2018
Alhashim, I., Xu, K., Zhuang, Y., et al.: Deformation-driven topology-varying 3D shape correspondence. ACM Trans. Graph. (TOG) 34(6), 236 (2015)
Kaick, O.V., Fish, N., Kleiman, Y., et al.: Shape segmentation by approximate convexity analysis. ACM Trans. Graph. (TOG) 34(1), 4 (2014)
Chen, D.Y., Tian, X.P., Shen, Y.T., et al.: On visual similarity based 3D model retrieval. Comput. Graph. Forum. 22(3), 223–232 (2003)
Shapira, L., Shamir, A., Cohen-Or, D.: Consistent mesh partitioning and skeletonisation using the shape diameter function. Vis. Comput. 24(4), 249 (2008)
Li, R., Wang, S., Zhu, F. et al.: Adaptive graph convolutional neural networks (2018). arXiv preprint arXiv:1801.03226
Srivastava, N., Hinton, G., Krizhevsky, A., et al.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)
He, K., Zhang, X., Ren S, et al.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Acknowledgements
This work was supported by National High Technology Research and Development Program of China (No. 2007AA01Z334), National Natural Science Foundation of China (Nos. 61321491 and 61272219), Program for New Century Excellent Talents in University of China (NCET-04-04605), the China Postdoctoral Science Foundation (Grant No. 2017M621700) and Innovation Fund of State Key Lab for Novel Software Technology (Nos. ZZKT2013A12, ZZKT2016A11 and ZZKT2018A09).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Lang, X., Sun, Z., Li, Q., Shi, J. (2018). Assembly-Based 3D Modeling Using Graph Convolutional Neural Networks. In: Hong, R., Cheng, WH., Yamasaki, T., Wang, M., Ngo, CW. (eds) Advances in Multimedia Information Processing – PCM 2018. PCM 2018. Lecture Notes in Computer Science(), vol 11166. Springer, Cham. https://doi.org/10.1007/978-3-030-00764-5_30
Download citation
DOI: https://doi.org/10.1007/978-3-030-00764-5_30
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-00763-8
Online ISBN: 978-3-030-00764-5
eBook Packages: Computer ScienceComputer Science (R0)