Deep Multi-scale Learning on Point Sets for 3D Object Recognition

  • Yang XiaoEmail author
  • Yanxin Ma
  • Min Zhou
  • Jun Zhang
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 875)


In recent years, point cloud data based 3D deep learning has become a popular method for three-dimensional object recognition. In this work, we introduce a multi-scale convolution neural network which takes point cloud as input for 3D object recognition. Our network structure consists of two parts which are the feature extraction structure and the feature processing part. Experiments are conducted on the ModelNet40 dataset with several state-of-the-art methods. The proposed method achieves a higher accuracy on 3D object recognition with 87.1%. Experimental results have demonstrated the superior performance of the proposed multi-scale feature learning network.


Point cloud Multi-scale Object recognition Feature learning 


  1. 1.
    Ioannidou, A., Chatzilari, E., Nikolopoulos, S., Kompatsiaris, I.: Deep learning advances in computer vision with 3D data: a survey. ACM Comput. Surv. 50(2), 20 (2017)CrossRefGoogle Scholar
  2. 2.
    Su, H., Maji, S., Kalogerakis, E., Learnedmiller, E.: Multi-view convolutional neural networks for 3D shape recognition, pp. 945–953 (2015)Google Scholar
  3. 3.
    Wu, Z., et al.: 3D ShapeNets: a deep representation for volumetric shapes. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1912–1920. IEEE (2014)Google Scholar
  4. 4.
    Qi, C.R., Su, H., Nießner, M., Dai, A., Yan, M., Guibas, L.J.: Volumetric and multi-view CNNs for object classification on 3D data. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 5648–5656. IEEE Computer Society (2016)Google Scholar
  5. 5.
    Maturana, D., Scherer, S.: VoxNet: a 3D convolutional neural network for real-time object recognition. In: IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 922–928. IEEE (2015)Google Scholar
  6. 6.
    Qi, C.R., Su, H., Mo, K., Guibas, L.J.: Pointnet: deep learning on point sets for 3D classification and segmentation arXiv preprint arXiv:1612.00593 (2016)
  7. 7.
    Kazhdan, M., Funkhouser, T., Rusinkiewicz, S.: Rotation invariant spherical harmonic representation of 3D shape descriptors. In: Eurographics/ACM SIGGRAPH Symposium on Geometry Processing, pp. 156–164. Eurographics Association (2003)Google Scholar
  8. 8.
    Sun, J., Ovsjanikov, M., Guibas, L.: A concise and provably informative multi-scale signature based on heat diffusion. In: Computer Graphics Forum, vol. 28, pp. 1383–1392 (2009)Google Scholar
  9. 9.
    Guo, Y., Bennamoun, M., Sohel, F., Lu, M., Wan, J.: 3D object recognition in cluttered scenes with local surface features: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 36(11), 2270–2287 (2014)CrossRefGoogle Scholar
  10. 10.
    Malassiotis, S., Strintzis, M.G.: Snapshots: a novel local surface descriptor and matching algorithm for robust 3D surface alignment. IEEE Trans. Pattern Anal. Mach. Intell. 29(7), 1285 (2007)CrossRefGoogle Scholar
  11. 11.
    Chua, C.S., Jarvis, R.: Point signatures: a new representation for 3D object recognition. Int. J. Comput. Vis. 25(1), 63–85 (1997)CrossRefGoogle Scholar
  12. 12.
    Guo, Y., Sohel, F.A., Bennamoun, M., Wan, J., Lu, M.: RoPS: a local feature descriptor for 3D rigid objects based on rotational projection statistics. In: International Conference on Communications, Signal Processing, and Their Applications, pp. 1–6. IEEE (2013)Google Scholar
  13. 13.
    Shi, B., Bai, S., Zhou, Z., Bai, X.: Deeppano: deep panoramic representation for 3-D shape recognition. IEEE Signal Process. Lett. 22(12), 2339–2343 (2015)CrossRefGoogle Scholar
  14. 14.
    Brock, A., Lim, T., Ritchie, J.M., Weston, N.: Generative and discriminative voxel modeling with convolutional neural networks. Comput. Sci. (2016)Google Scholar
  15. 15.
    Sedaghat, N., Zolfaghari, M., Amiri, E., Brox, T.: Orientation-boosted voxel nets for 3D object recognition. arXiv preprint arXiv:1604.03351 (2016)
  16. 16.
    Qi, C.R., Yi, L., Su, H., Guibas, L.J.: Pointnet++: deep hierarchical feature learning on point sets in a metric space. arXiv preprint arXiv:1706.02413 (2017)
  17. 17.
    Johns, E., Leutenegger, S., Davison, A.J.: Pairwise decomposition of image sequences for active multi-view recognition. arXiv preprint arXiv:1605.08359 (2016)

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  1. 1.College of Electronic Science and EngineeringNational University of Defense TechnologyChangshaChina
  2. 2.Branch 72 of No. 32142 ArmyBaodingChina

Personalised recommendations