Advertisement

CN: Channel Normalization for Point Cloud Recognition

Conference paper
  • 715 Downloads
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12355)

Abstract

In 3D recognition, to fuse multi-scale structure information, existing methods apply hierarchical frameworks stacked by multiple fusion layers for integrating current relative locations with structure information from the previous level. In this paper, we deeply analyze these point recognition frameworks and present a factor, called difference ratio, to measure the influence of structure information among different levels on the final representation. We discover that structure information in deeper layers is overwhelmed by information in shallower layers in generating the final features, which prevents the model from understanding the point cloud in a global view. Inspired by this observation, we propose a novel channel normalization scheme to balance structure information among different layers and avoid excessive accumulation of shallow information, which benefits the model in exploiting and integrating multilayer structure information. We evaluate our channel normalization in several core 3D recognition tasks including classification, segmentation and detection. Experimental results show that our channel normalization further boosts the performance of state-of-the-art methods effectively.

Keywords

3D recognition Point cloud Object detection Classification 

References

  1. 1.
    Chen, Q., Sun, L., Wang, Z., Jia, K., Yuille, A.: Object as hotspots: an anchor-free 3D object detection approach via firing of hotspots (2019)Google Scholar
  2. 2.
    Chen, Y., Liu, S., Shen, X., Jia, J.: Fast point R-CNN. In: Proceedings of the ICCV (2019)Google Scholar
  3. 3.
    Feng, Y., Zhang, Z., Zhao, X., Ji, R., Gao, Y.: GVCNN: group-view convolutional neural networks for 3D shape recognition. In: Proceedings of the CVPR (2018)Google Scholar
  4. 4.
    Geiger, A., Lenz, P., Stiller, C., Urtasun, R.: Vision meets robotics: the KITTI dataset. Int. J. Robot. Res. 32, 1231–1237 (2013)CrossRefGoogle Scholar
  5. 5.
    Guo, H., Wang, J., Gao, Y., Li, J., Lu, H.: Multi-view 3D object retrieval with deep embedding network. IEEE Trans. Image Process. 25, 5526–5537 (2016)MathSciNetCrossRefGoogle Scholar
  6. 6.
    Klokov, R., Lempitsky, V.S.: Escape from cells: deep Kd-networks for the recognition of 3D point cloud models. In: Proceedings of the ICCV (2017)Google Scholar
  7. 7.
    Kuang, H., Wang, B., An, J., Zhang, M., Zhang, Z.: Voxel-FPN: multi-scale voxel feature aggregation in 3D object detection from point clouds. Sensors 20, 704 (2020)CrossRefGoogle Scholar
  8. 8.
    Lang, A.H., Vora, S., Caesar, H., Zhou, L., Yang, J., Beijbom, O.: PointPillars: fast encoders for object detection from point clouds. In: Proceedings of the CVPR (2019)Google Scholar
  9. 9.
    Li, R., Li, X., Fu, C., Cohen-Or, D., Heng, P.: PU-GAN: a point cloud upsampling adversarial network. CoRR (2019)Google Scholar
  10. 10.
    Li, Y., Bu, R., Sun, M., Chen, B.: PointCNN. CoRR (2018)Google Scholar
  11. 11.
    Liang, M., Yang, B., Wang, S., Urtasun, R.: Deep continuous fusion for multi-sensor 3D object detection. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11220, pp. 663–678. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01270-0_39CrossRefGoogle Scholar
  12. 12.
    Liu, X., Qi, C.R., Guibas, L.J.: FlowNet3D: learning scene flow in 3D point clouds. In: Proceedings of the CVPR (2019)Google Scholar
  13. 13.
    Liu, Y., Fan, B., Meng, G., Lu, J., Xiang, S., Pan, C.: DensePoint: learning densely contextual representation for efficient point cloud processing. In: Proceedings of the ICCV (2019)Google Scholar
  14. 14.
    Liu, Y., Fan, B., Xiang, S., Pan, C.: Relation-shape convolutional neural network for point cloud analysis. In: Proceedings of the CVPR (2019)Google Scholar
  15. 15.
    Liu, Z., Zhao, X., Huang, T., Hu, R., Zhou, Y., Bai, X.: TANet: robust 3D object detection from point clouds with triple attention. AAAI (2020)Google Scholar
  16. 16.
    Mao, J., Wang, X., Li, H.: Interpolated convolutional networks for 3D point cloud understanding. In: Proceedings of the ICCV (2019)Google Scholar
  17. 17.
    Maturana, D., Scherer, S.: VoxNet: a 3D convolutional neural network for real-time object recognition. In: Proceedings of the IROS (2015)Google Scholar
  18. 18.
    Qi, C.R., Liu, W., Wu, C., Su, H., Guibas, L.J.: Frustum pointnets for 3D object detection from RGB-D data. CoRR (2017)Google Scholar
  19. 19.
    Qi, C.R., Su, H., Mo, K., Guibas, L.J.: PointNet: deep learning on point sets for 3D classification and segmentation. In: Proceedings of the CVPR (2017)Google Scholar
  20. 20.
    Qi, C.R., Yi, L., Su, H., Guibas, L.J.: PointNet++: deep hierarchical feature learning on point sets in a metric space. In: Proceedings of the NIPS (2017)Google Scholar
  21. 21.
    Shen, Y., Feng, C., Yang, Y., Tian, D.: Mining point cloud local structures by kernel correlation and graph pooling. In: Proceedings of the CVPR (2018)Google Scholar
  22. 22.
    Shi, S., Wang, X., Li, H.: PointRCNN: 3D object proposal generation and detection from point cloud. In: Proceedings of the CVPR (2019)Google Scholar
  23. 23.
    Srivastava, N., Hinton, G.E., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15, 1929–1958 (2014)MathSciNetzbMATHGoogle Scholar
  24. 24.
    Su, H., et al.: SPLATNet: sparse lattice networks for point cloud processing. In: Proceedings of the CVPR (2018)Google Scholar
  25. 25.
    Su, H., Maji, S., Kalogerakis, E., Learned-Miller, E.G.: Multi-view convolutional neural networks for 3D shape recognition. In: Proceedings of the ICCV (2015)Google Scholar
  26. 26.
    Thomas, H., Qi, C.R., Deschaud, J., Marcotegui, B., Goulette, F., Guibas, L.J.: KPConv: flexible and deformable convolution for point clouds. In: Proceedings of the ICCV (2019)Google Scholar
  27. 27.
    Wang, C., Samari, B., Siddiqi, K.: Local spectral graph convolution for point set feature learning. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 56–71. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01225-0_4CrossRefGoogle Scholar
  28. 28.
    Wang, Y., Sun, Y., Liu, Z., Sarma, S.E., Bronstein, M.M., Solomon, J.M.: Dynamic graph CNN for learning on point clouds. ACM Trans. Graph. 38, 1–12 (2019)Google Scholar
  29. 29.
    Wu, W., Qi, Z., Li, F.: PointConv: deep convolutional networks on 3D point clouds. In: Proceedings of the CVPR (2019)Google Scholar
  30. 30.
    Wu, Z., et al.: 3D shapeNets: a deep representation for volumetric shapes. In: Proceedings of the CVPR (2015)Google Scholar
  31. 31.
    Yan, Y., Mao, Y., Li, B.: Second: sparsely embedded convolutional detection. Sensors 18, 3337 (2018)CrossRefGoogle Scholar
  32. 32.
    Yang, Z., Sun, Y., Liu, S., Jia, J.: 3DSSD: point-based 3D single stage object detector (2020)Google Scholar
  33. 33.
    Yang, Z., Sun, Y., Liu, S., Shen, X., Jia, J.: STD: sparse-to-dense 3D object detector for point cloud. In: Proceedings of the ICCV (2019)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.The Chinese University of Hong KongShatinThe People’s Republic of China
  2. 2.Hong Kong University of Science and TechnologyKowloonHong Kong
  3. 3.SmartMoreShenzhenChina
  4. 4.The University of Hong KongPokfulamHong Kong

Personalised recommendations