Skip to main content

Deformable Point Cloud Recognition Using Intrinsic Function and Deep Learning

  • Conference paper
  • First Online:
Advances in Multimedia Information Processing – PCM 2018 (PCM 2018)

Part of the book series: Lecture Notes in Computer Science ((LNISA,volume 11165))

Included in the following conference series:

  • 2606 Accesses

Abstract

Recognizing 3D point cloud shapes under isometric deformation is an interesting and challenging issue in the geometry field. This paper proposes a novel feature learning approach by using both the model-based intrinsic descriptor and the deep learning technique. Instead of directly applying deep convolutional neural networks (CNN) on point clouds, we first represent the isometric deformation by using a set of local intrinsic functions to grasp the invariant properties of the shape. Then, an effective point CNN network is developed to learn the parameters and perform semantic feature learning in an end-to-end fashion to link the local and global information together for discriminative shape representation and classification. To reduce the computational costs of our CNN network, some simple operations, like downsampling and fusion, are applied to decrease the number of points and the intrinsic dimensions based on our average heat function. The experimental results on multiple standard benchmarks have demonstrated that our proposed algorithm can achieve very competitive results on both the accuracy rates and the computational efficiency.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Bronstein, A.M., Bronstein, M.M., Guibas, L.J., et al.: Shape google: Geometric words and expressions for invariant shape retrieval. ACM Trans. Graph. 30(1), 1 (2011)

    Article  Google Scholar 

  2. Bu, S., Wang, L., Han, P., et al.: 3d shape recognition and retrieval based on multi-modality deep learning. Neurocomputing (2017)

    Google Scholar 

  3. Coifman, R.R., Lafon, S.: Diffusion maps. Appl. Comput. Harmonic Anal. 21(1), 5–30 (2006)

    Article  MathSciNet  Google Scholar 

  4. Fukui, A., Park, D.H., Yang, D., et al.: Multimodal compact bilinear pooling for visual question answering and visual grounding. arXiv preprint arXiv:1606.01847 (2016)

  5. Kuang, Z., Li, Z., Jiang, X.: Retrieval of non-rigid 3D shapes from multiple aspects. Comput.-Aided Des. 58(C), 13–23 (2015)

    Article  Google Scholar 

  6. Kuang, Z., Yu, J., Li, Z., Zhang, B., Fan, J.: Integrating multi-level deep learning and concept ontology for large-scale visual recognition. Pattern Recognit. 78, 198–214 (2018)

    Article  Google Scholar 

  7. Laga, H., Schreck, T., Ferreira, A., et al.: Bag of words and local spectral descriptor for 3D partial shape retrieval. In: Eurographics Workshop on 3D Object Retrieval, pp. 41–48. Citeseer (2011)

    Google Scholar 

  8. Lian, Z., Godil, A., Bustos, B.: A comparison of methods for non-rigid 3D shape retrieval. Pattern Recognit. 46(1), 449–461 (2013)

    Article  Google Scholar 

  9. Lian, Z., Godil, A., Fabry, T., et al.: Shrec’10 track: Non-rigid 3D shape retrieval. In: Eurographics Workshop on 3D Object Retrieval, vol. 10, pp. 101–108. The Eurographics Association (2010)

    Google Scholar 

  10. Lian, Z., Zhang, J., Choi, S., et al.: Shrec’15 track: non-rigid 3D shape retrieval. In: Eurographics Workshop on 3D Object Retrieval. The Eurographics Association (2015)

    Google Scholar 

  11. Liang, J., Lai, R., Wong, T.W., et al.: Geometric understanding of point clouds using laplace-beltrami operator. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 214–221. IEEE (2012)

    Google Scholar 

  12. Limberger, F., Wilson, R., Aono, M., et al.: Point-cloud shape retrieval of non-rigid toys. In: Eurographics Workshop on 3D Object Retrieval. The Eurographics Association (2017)

    Google Scholar 

  13. van der Maaten, L., Hinton, G.: Visualizing non-metric similarities in multiple maps. Mach. Learn. 1(87), 33–55 (2012)

    Article  MathSciNet  Google Scholar 

  14. Mahmoudi, M., Sapiro, G.: Three-dimensional point cloud recognition via distributions of geometric distances. Graph. Models 71(1), 22–31 (2009)

    Article  Google Scholar 

  15. Maron, H., Galun, M., Aigerman, N., et al.: Convolutional neural networks on surfaces via seamless toric covers. ACM Trans. Graph. 36(71) (2017)

    Article  Google Scholar 

  16. Osada, R., Funkhouser, T., Chazelle, B.: Shape distributions. ACM Trans. Graph. 21(4), 807–832 (2002)

    Article  MathSciNet  Google Scholar 

  17. Qi, C.R., Su, H., Mo, K., Guibas, L.J.: Pointnet: Deep learning on point sets for 3D classification and segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition (2017)

    Google Scholar 

  18. Reuter, M., Wolter, F.E., Peinecke, N.: Laplace-beltrami spectra as Shape-DNA of surfaces and solids. Comput.-Aided Des. 38(4), 342–366 (2006)

    Article  Google Scholar 

  19. Rustamov, R.M.: Laplace-beltrami eigenfunctions for deformation invariant shape representation. In: Eurographics Symposium on Geometry Processing, pp. 225–233. Eurographics Association (2007)

    Google Scholar 

  20. Su, H., Maji, S., Kalogerakis, E., et al.: Multi-view convolutional neural networks for 3D shape recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 945–953. IEEE (2015)

    Google Scholar 

  21. Sun, J., Ovsjanikov, M., Guibas, L.: A concise and provably informative multi-scale signature based on heat diffusion. Comput. Graph. Forum 28(5), 1383–1392 (2009)

    Article  Google Scholar 

  22. Tabia, H., Picard, D., Laga, H., et al.: Compact vectors of locally aggregated tensors for 3D shape retrieval. In: Eurographics Workshop on 3D Object Retrieval, pp. 17–24. The Eurographics Association (2013)

    Google Scholar 

  23. Wu, Z., Song, S., Khosla, A., et al.: 3d shapenets: a deep representation for volumetric shapes. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1912–1920 (2015)

    Google Scholar 

  24. Xie, J., Dai, G., Zhu, F.: Deepshape: deep-learned shape descriptor for 3D shape retrieval. IEEE Trans. Pattern Anal. Mach. Intell. 39(7), 1335–1345 (2017)

    Article  Google Scholar 

  25. Yu, J., Tao, D., Wang, M.: Learning to rank using user clicks and visual features for image retrieval. IEEE Trans. Cybern. 45(4), 767–779 (2015)

    Article  Google Scholar 

  26. Yu, J., Yang, X., Gao, F.: Deep multimodal distance metric learning using click constraints for image ranking. IEEE Trans. Cybern. 47(12), 4014–4024 (2017)

    Article  Google Scholar 

Download references

Acknowledgements

This work is partly supported by National Natural Science Foundation of China under Grants 61806063, 61772161, 61622205, 61472110, 61602136 and the Zhejiang Provincial Natural Science Foundation of China under Grant LR15F020002. The authors would like to thank the reviewers and editors for their insightful comments and valuable suggestions which have led to substantial improvements of the paper.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Jun Yu .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2018 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Kuang, Z., Yu, J., Zhu, S., Li, Z., Fan, J. (2018). Deformable Point Cloud Recognition Using Intrinsic Function and Deep Learning. 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 11165. Springer, Cham. https://doi.org/10.1007/978-3-030-00767-6_9

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-00767-6_9

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-00766-9

  • Online ISBN: 978-3-030-00767-6

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics