Abstract
This paper is devoted to signal processing on point-clouds by means of neural networks. Nowadays, state-of-the-art in image processing and computer vision is mostly based on training deep convolutional neural networks on large datasets. While it is also the case for the processing of point-clouds with Graph Neural Networks (GNN), the focus has been largely given to high-level tasks such as classification and segmentation using supervised learning on labeled datasets such as ShapeNet. Yet, such datasets are scarce and time-consuming to build depending on the target application. In this work, we investigate the use of variational models for such GNN to process signals on graphs for unsupervised learning.
Our contributions are two-fold. We first show that some existing variational - based algorithms for signals on graphs can be formulated as Message Passing Networks (MPN), a particular instance of GNN, making them computationally efficient in practice when compared to standard gradient-based machine learning algorithms. Secondly, we investigate the unsupervised learning of feed-forward GNN, either by direct optimization of an inverse problem or by model distillation from variational-based MPN.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Bertocchi, C., Chouzenoux, E., Corbineau, M.C., Pesquet, J.C., Prato, M.: Deepunfolding of a proximal interior point method for image restoration. Inverse Probl. 36(3), 034005 (2020)
Bruna, J., Zaremba, W., Szlam, A., LeCun, Y.: Spectral networks and locally connected networks on graphs. In: International Conference on Learning Representations (2014)
Chambolle, A., Pock, T.: A first-order primal-dual algorithm for convex problems with applications to imaging. J. Math. Imaging Vis. 40(1), 120–145 (2011)
Combettes, P.L., Pesquet, J.C.: Deep neural network structures solving variational inequalities. In: Set-Valued and Variational Analysis, pp. 1–28 (2020)
Defferrard, M., Bresson, X., Vandergheynst, P.: Convolutional neural networks on graphs with fast localized spectral filtering. In: Advances in Neural Information Processing Systems, pp. 3844–3852 (2016)
Elmoataz, A., Lezoray, O., Bougleux, S.: Nonlocal discrete regularization on weighted graphs: a framework for image and manifold processing. IEEE Trans. Image Process. 17(7), 1047–1060 (2008)
Elmoataz, A., Toutain, M., Tenbrinck, D.: On the \(p\)-Laplacian and \(\infty \)-Laplacian on graphs with applications in image and data processing. SIAM J. Imag. Sci. 8(4), 2412–2451 (2015)
Fey, M., Lenssen, J.E.: Fast graph representation learning with pytorch geometric. arXiv preprint arXiv:1903.02428 (2019)
Gilboa, G., Osher, S.: Nonlocal operators with applications to image processing. Multiscale Model. Simul. 7(3), 1005–1028 (2009)
Gilmer, J., Schoenholz, S.S., Riley, P.F., Vinyals, O., Dahl, G.E.: Neural message passing for quantum chemistry. In: ICML (2017)
Hasannasab, M., Hertrich, J., Neumayer, S., Plonka, G., Setzer, S., Steidl, G.: Parseval proximal neural networks. J. Fourier Anal. Appl. 26(4), 1–31 (2020)
Hidane, M., Lézoray, O., Elmoataz, A.: Nonlinear multilayered representation of graph-signals. J. Math. Imaging Vis. 45(2), 114–137 (2013)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Proceedings of the 3rd International Conference on Learning Representations (ICLR) (2014)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: International Conference on Learning Representations (2017)
Kobler, E., Klatzer, T., Hammernik, K., Pock, T.: Variational networks: connecting variational methods and deep learning. In: Roth, V., Vetter, T. (eds.) GCPR 2017. LNCS, vol. 10496, pp. 281–293. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-66709-6_23
Li, R., Li, X., Fu, C.W., Cohen-Or, D., Heng, P.A.: PU-GAN: a point cloud upsampling adversarial network. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 7203–7212 (2019)
Liu, D.C., Nocedal, J.: On the limited memory BFGS method for large scale optimization. Math. Program. 45(1), 503–528 (1989)
Lozes, F., Hidane, M., Elmoataz, A., Lézoray, O.: Nonlocal segmentation of point clouds with graphs. In: 2013 IEEE Global Conference on Signal and Information Processing, pp. 459–462. IEEE (2013)
Meinhardt, T., Moller, M., Hazirbas, C., Cremers, D.: Learning proximal operators: using denoising networks for regularizing inverse imaging problems. In: Proceedings of the IEEE ICCV, pp. 1781–1790 (2017)
Peyré, G., Bougleux, S., Cohen, L.: Non-local regularization of inverse problems. Inverse Probl. Imag. 5(2), 511 (2011)
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 IEEE Conference on Computer Vision and Pattern Recognition, pp. 652–660 (2017)
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, vol. 30 (2017)
Raguet, H., Landrieu, L.: Preconditioning of a generalized forward-backward splitting and application to optimization on graphs. SIAM J. Imag. Sci. 8(4), 2706–2739 (2015)
Raguet, H., Landrieu, L.: Cut-pursuit algorithm for regularizing nonsmooth functionals with graph total variation. In: International Conference on Machine Learning, pp. 4247–4256 (2018)
Tabti, S., Rabin, J., Elmoataz, A.: Symmetric upwind scheme for discrete weighted total variation. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1827–1831 (2018)
Tenbrinck, D., Gaede, F., Burger, M.: Variational graph methods for efficient point cloud sparsification. arXiv preprint arXiv:1903.02858 (2019)
Wang, Y., Solomon, J.M.: Deep closest point: learning representations for point cloud registration. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3523–3532 (2019)
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. (TOG) 38(5), 1–12 (2019)
Williams, F., Schneider, T., Silva, C., Zorin, D., Bruna, J., Panozzo, D.: Deep geometric prior for surface reconstruction. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 10130–10139 (2019)
Wu, F., Souza, A., Zhang, T., Fifty, C., Yu, T., Weinberger, K.: Simplifying graph convolutional networks. In: Proceedings of the 36th International Conference on Machine Learning, vol. 97, pp. 6861–6871. PMLR (2019)
Yang, G., Huang, X., Hao, Z., Liu, M.Y., Belongie, S., Hariharan, B.: PointFlow: 3D point cloud generation with continuous normalizing flows. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4541–4550 (2019)
Yi, L., et al.: A scalable active framework for region annotation in 3D shape collections. ACM Trans. Graph. (ToG) 35(6), 1–12 (2016)
Acknowledgments
This work has been carried out with financial support from the French Research Agency through the SUMUM project (ANR-17-CE38-0004)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Azad, A., Rabin, J., Elmoataz, A. (2021). Variational Models for Signal Processing with Graph Neural Networks. In: Elmoataz, A., Fadili, J., Quéau, Y., Rabin, J., Simon, L. (eds) Scale Space and Variational Methods in Computer Vision. SSVM 2021. Lecture Notes in Computer Science(), vol 12679. Springer, Cham. https://doi.org/10.1007/978-3-030-75549-2_26
Download citation
DOI: https://doi.org/10.1007/978-3-030-75549-2_26
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-75548-5
Online ISBN: 978-3-030-75549-2
eBook Packages: Computer ScienceComputer Science (R0)