Multi-kernel Diffusion CNNs for Graph-Based Learning on Point Clouds

  • Lasse HansenEmail author
  • Jasper Diesel
  • Mattias P. Heinrich
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11131)


Graph convolutional networks are a new promising learning approach to deal with data on irregular domains. They are predestined to overcome certain limitations of conventional grid-based architectures and will enable efficient handling of point clouds or related graphical data representations, e.g. superpixel graphs. Learning feature extractors and classifiers on 3D point clouds is still an underdeveloped area and has potential restrictions to equal graph topologies. In this work, we derive a new architectural design that combines rotationally and topologically invariant graph diffusion operators and node-wise feature learning through \(1\times 1\) convolutions. By combining multiple isotropic diffusion operations based on the Laplace-Beltrami operator, we can learn an optimal linear combination of diffusion kernels for effective feature propagation across nodes on an irregular graph. We validated our approach for learning point descriptors as well as semantic classification on real 3D point clouds of human poses and demonstrate an improvement from 85% to 95% in Dice overlap with our multi-kernel approach.


Graph convolutional networks Point descriptor learning Point cloud segmentation 


  1. 1.
    Atwood, J., Towsley, D.: Diffusion-convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1993–2001 (2016)Google Scholar
  2. 2.
    Aubry, M., Schlickewei, U., Cremers, D.: The wave kernel signature: a quantum mechanical approach to shape analysis. In: 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops), pp. 1626–1633. IEEE (2011)Google Scholar
  3. 3.
    Bogo, F., Romero, J., Loper, M., Black, M.J.: FAUST: dataset and evaluation for 3D mesh registration. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3794–3801 (2014)Google Scholar
  4. 4.
    Boscaini, D., Masci, J., Melzi, S., Bronstein, M.M., Castellani, U., Vandergheynst, P.: Learning class-specific descriptors for deformable shapes using localized spectral convolutional networks. In: Computer Graphics Forum, vol. 34, pp. 13–23. Wiley Online Library (2015)Google Scholar
  5. 5.
    Boscaini, D., Masci, J., Rodolà, E., Bronstein, M.: Learning shape correspondence with anisotropic convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 3189–3197 (2016)Google Scholar
  6. 6.
    Bronstein, M.M., Bruna, J., LeCun, Y., Szlam, A., Vandergheynst, P.: Geometric deep learning: going beyond euclidean data. IEEE Signal Process. Mag. 34(4), 18–42 (2017)CrossRefGoogle Scholar
  7. 7.
    Bruna, J., Zaremba, W., Szlam, A., Lecun, Y.: Spectral networks and locally connected networks on graphs. In: International Conference on Learning Representations (ICLR 2014), CBLS, April 2014Google Scholar
  8. 8.
    Calonder, M., Lepetit, V., Strecha, C., Fua, P.: BRIEF: binary robust independent elementary features. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6314, pp. 778–792. Springer, Heidelberg (2010). Scholar
  9. 9.
    Chung, F.R., Graham, F.C.: Spectral Graph Theory. No. 92, American Mathematical Society (1997)Google Scholar
  10. 10.
    Desbrun, M., Meyer, M., Schröder, P., Barr, A.H.: Implicit fairing of irregular meshes using diffusion and curvature flow. In: Proceedings of the 26th Annual Conference on Computer Graphics and Interactive Techniques, pp. 317–324. ACM Press/Addison-Wesley Publishing Co. (1999)Google Scholar
  11. 11.
    Henaff, M., Bruna, J., LeCun, Y.: Deep convolutional networks on graph-structured data. arXiv preprint arXiv:1506.05163 (2015)
  12. 12.
    Kim, V.G., Lipman, Y., Funkhouser, T.: Blended intrinsic maps. In: ACM Transactions on Graphics (TOG), vol. 30, p. 79. ACM (2011)CrossRefGoogle Scholar
  13. 13.
    Kingma, D.P., Ba, J.L.: Adam: A method for stochastic optimization. In: Proceedings of the 3rd International Conference on Learning Representations (2014)Google Scholar
  14. 14.
    Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)
  15. 15.
    Kleiman, Y., Ovsjanikov, M.: Robust structure-based shape correspondence. In: Computer Graphics Forum. Wiley Online Library (2018)Google Scholar
  16. 16.
    Krähenbühl, P., Koltun, V.: Efficient inference in fully connected CRFs with Gaussian edge potentials. In: Advances in neural information processing systems, pp. 109–117 (2011)Google Scholar
  17. 17.
    Litman, R., Bronstein, A.M.: Learning spectral descriptors for deformable shape correspondence. IEEE Trans. Pattern Anal. Mach. Intell. 36(1), 171–180 (2014)CrossRefGoogle Scholar
  18. 18.
    Masci, J., Boscaini, D., Bronstein, M., Vandergheynst, P.: Geodesic convolutional neural networks on Riemannian manifolds. In: Proceedings of the IEEE International Conference on Computer Vision Workshops, pp. 37–45 (2015)Google Scholar
  19. 19.
    Maturana, D., Scherer, S.: VoxNet: A 3D convolutional neural network for real-time object recognition. In: 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 922–928. IEEE (2015)Google Scholar
  20. 20.
    Monti, F., Boscaini, D., Masci, J., Rodola, E., Svoboda, J., Bronstein, M.M.: Geometric deep learning on graphs and manifolds using mixture model CNNs. In: Proceedings of the CVPR, vol. 1, p. 3 (2017)Google Scholar
  21. 21.
    Paszke, A., et al.: Automatic differentiation in PyTorch. In: NIPS-W (2017)Google Scholar
  22. 22.
    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 Computer Vision and Pattern Recognition (CVPR), vol. 1(2), p. 4. IEEE (2017)Google Scholar
  23. 23.
    Qi, C.R., Yi, L., Su, H., Guibas, L.J.: PointNet++: deep hierarchical feature learning on point sets in a metric space. In: Advances in Neural Information Processing Systems, pp. 5099–5108 (2017)Google Scholar
  24. 24.
    Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91–99 (2015)Google Scholar
  25. 25.
    Rusu, R.B., Blodow, N., Beetz, M.: Fast point feature histograms (FPFH) for 3D registration. In: 2009 IEEE International Conference on Robotics and Automation, ICRA 2009, pp. 3212–3217. Citeseer (2009)Google Scholar
  26. 26.
    Sen, P., Namata, G., Bilgic, M., Getoor, L., Galligher, B., Eliassi-Rad, T.: Collective classification in network data. AI Mag. 29(3), 93 (2008)CrossRefGoogle Scholar
  27. 27.
    Su, H., Maji, S., Kalogerakis, E., Learned-Miller, E.: Multi-view convolutional neural networks for 3D shape recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 945–953 (2015)Google Scholar
  28. 28.
    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. Wiley Online Library (2009)Google Scholar
  29. 29.
    Velickovic, P., et al.: Graph attention networks. arXiv preprint arXiv:1710.10903 1.2 (2017)

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Lasse Hansen
    • 1
    Email author
  • Jasper Diesel
    • 2
  • Mattias P. Heinrich
    • 1
  1. 1.Institute of Medical InformaticsUniversity of LübeckLübeckGermany
  2. 2.Drägerwerk AG & Co. KGaALübeckGermany

Personalised recommendations