Abstract
Recently, emerging point cloud dedicated deep learning frameworks, such as PointNet and PointNet++, have achieved remarkable advantage in both accuracy and speed over traditional handcrafted ones. However, since the point coordinates of point clouds are represented in various local coordinate systems, most existing methods require additional preprocessing on raw point clouds. In this work, we design an efficient transform-invariant framework (named 3DTI-Net) for point cloud processing without the need of such preprocessing. 3DTI-Net consists of a transform invariant feature encoder as the front-end and a hierarchical graph convolutional neural network as the back-end. It achieves transform invariant feature extraction by learning inner 3D geometry information based on local graph representation. Experiments results on various classification and retrieval tasks show that, 3DTI-Net is able to learn 3D feature efficiently and can achieve state-of-the-art performance in rotated 3D object classification and retrieval.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Aldoma, A., et al.: Tutorial: point cloud library: three-dimensional object recognition and 6 dof pose estimation. IEEE Robot. Autom. Mag. 19(3), 80–91 (2012)
Bai, S., Bai, X., Zhou, Z., Zhang, Z., Latecki, L.J.: Gift: a real-time and scalable 3D shape search engine. In: Computer Vision and Pattern Recognition, pp. 5023–5032 (2016)
Belongie, S.J., Malik, J., Puzicha, J.: Shape context: a new descriptor for shape matching and object recognition, pp. 831–837 (2000)
Bruna, J., Zaremba, W., Szlam, A., Lecun, Y.: Spectral networks and locally connected networks on graphs. In: International Conference on Learning Representations (2014)
Chang, A.X., et al.: ShapeNet: an information-rich 3D model repository. arXiv Graphics (2015)
Qi, C.R., Su, H., Mo, K., Guibas, L.J.: PointNet: deep learning on point sets for 3D classification and segmentation. In: Computer Vision and Pattern Recognition, pp. 77–85 (2017)
Cohen, T.S., Geiger, M., Kohler, J., Welling, M.: Spherical CNNS. In: International Conference on Learning Representations (2018)
Defferrard, M., Bresson, X., Vandergheynst, P.: Convolutional neural networks on graphs with fast localized spectral filtering. In: Neural Information Processing Systems, pp. 3844–3852 (2016)
Deng, H., Birdal, T., Ilic, S.: PPFNet: global context aware local features for robust 3D point matching (2018)
Esteves, C., Allenblanchette, C., Makadia, A., Daniilidis, K.: Learning SO(3) equivariant representations with spherical CNNs. arXiv Computer Vision and Pattern Recognition (2017)
Furuya, T., Ohbuchi, R.: Deep aggregation of local 3D geometric features for 3D model retrieval. In: British Machine Vision Conference, pp. 121.1–121.12 (2016)
Jaderberg, M., Simonyan, K., Zisserman, A., et al.: Spatial transformer networks. In: Advances in Neural Information Processing Systems, pp. 2017–2025 (2015)
Johnson, A.E., Hebert, M.: Using spin images for efficient object recognition in cluttered 3d scenes. IEEE Trans. Pattern Anal. Mach. Intell. 21(5), 433–449 (1999)
Kanezaki, A., Matsushita, Y., Nishida, Y.: RotationNet: joint object categorization and pose estimation using multiviews from unsupervised viewpoints. In: Computer Vision and Pattern Recognition (2018)
Li, Y., Bu, R., Sun, M., Wu, W., Di, X., Chen, B.: PointCNN: convolution on x-transformed points. In: NeurIPS (2018)
Maturana, D., Scherer, S.: VoxNet: a 3D convolutional neural network for real-time object recognition, pp. 922–928 (2015)
Ortega, A., Frossard, P., Kovacevic, J., Moura, J.M.F., Vandergheynst, P.: Graph signal processing: overview, challenges, and applications. Proc. IEEE 106(5), 808–828 (2017)
Qi, C.R., Su, H., Niebner, M., Dai, A., Yan, M., Guibas, L.J.: Volumetric and multi-view CNNs for object classification on 3D data. In: Computer Vision and Pattern Recognition, pp. 5648–5656 (2016)
Qi, C.R., Yi, L., Su, H., Guibas, L.J.: PointNet++: deep hierarchical feature learning on point sets in a metric space. In: Neural Information Processing Systems, pp. 5099–5108 (2017)
Rusu, R.B., Blodow, N., Beetz, M.: Fast point feature histograms (FPFH) for 3D registration, pp. 1848–1853 (2009)
Rusu, R.B., Blodow, N., Marton, Z., Beetz, M.: Aligning point cloud views using persistent feature histograms, pp. 3384–3391 (2008)
Sandryhaila, A., Moura, J.M.F.: Discrete signal processing on graphs. IEEE Trans. Signal Process. 61(7), 1644–1656 (2013)
Savva, M., et al.: Large-scale 3D shape retrieval from ShapeNet Core55. In: 3DOR (2017)
Su, H., Maji, S., Kalogerakis, E., Learnedmiller, E.G.: Multi-view convolutional neural networks for 3D shape recognition. In: International Conference on Computer Vision, pp. 945–953 (2015)
Tatsuma, A., Aono, M.: Multi-fourier spectra descriptor and augmentation with spectral clustering for 3D shape retrieval. Vis. Comput. 25(8), 785–804 (2009)
Te, G., Hu, W., Zheng, A., Guo, Z.: RGCNN: regularized graph CNN for point cloud segmentation. In: ACM multimedia (2018)
Tombari, F., Salti, S., Di Stefano, L.: Unique signatures of histograms for local surface description. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6313, pp. 356–369. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-15558-1_26
Wang, Y., Sun, Y., Liu, Z., Sarma, S.E., Bronstein, M.M., Solomon, J.: Dynamic graph CNN for learning on point clouds. arXiv Computer Vision and Pattern Recognition (2018)
Wen, F., Chu, L., Liu, P., Qiu, R.: A survey on nonconvex regularization based sparse and low-rank recovery in signal processing, statistics, and machine learning. IEEE Access 1 (2018). https://doi.org/10.1109/ACCESS.2018.2880454
Wu, Z., et al.: 3D ShapeNets: a deep representation for volumetric shapes. In: Computer Vision and Pattern Recognition, pp. 1912–1920 (2015)
Yi, L., Su, H., Guo, X., Guibas, L.J.: SyncSpecCNN: synchronized spectral CNN for 3D shape segmentation. In: Computer Vision and Pattern Recognition, pp. 6584–6592 (2017)
Zeng, A., Song, S., Nießner, M., Fisher, M., Xiao, J., Funkhouser, T.: 3DMatch: learning local geometric descriptors from RGB-D reconstructions. In: CVPR (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
AÂ Appendix
AÂ Appendix
1.1 A.1Â Proof of Property 1
Proof
Translation invariance can be easily achieved by the re-centering operation, To prove rotation invariance, let \({R} \in \mathbb {R}^{3 \times 3}\) be an arbitrary rotation matrix, and the rotated point cloud coordinates is XR. Then, the i-th feature satisfies:
\(\square \)
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Pan, G., Liu, P., Wang, J., Ying, R., Wen, F. (2019). 3DTI-Net: Learn 3D Transform-Invariant Feature Using Hierarchical Graph CNN. In: Nayak, A., Sharma, A. (eds) PRICAI 2019: Trends in Artificial Intelligence. PRICAI 2019. Lecture Notes in Computer Science(), vol 11671. Springer, Cham. https://doi.org/10.1007/978-3-030-29911-8_4
Download citation
DOI: https://doi.org/10.1007/978-3-030-29911-8_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-29910-1
Online ISBN: 978-3-030-29911-8
eBook Packages: Computer ScienceComputer Science (R0)