Advertisement

Learning Graph-Convolutional Representations for Point Cloud Denoising

Conference paper
  • 650 Downloads
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12365)

Abstract

Point clouds are an increasingly relevant data type but they are often corrupted by noise. We propose a deep neural network based on graph-convolutional layers that can elegantly deal with the permutation-invariance problem encountered by learning-based point cloud processing methods. The network is fully-convolutional and can build complex hierarchies of features by dynamically constructing neighborhood graphs from similarity among the high-dimensional feature representations of the points. When coupled with a loss promoting proximity to the ideal surface, the proposed approach significantly outperforms state-of-the-art methods on a variety of metrics. In particular, it is able to improve in terms of Chamfer measure and of quality of the surface normals that can be estimated from the denoised data. We also show that it is especially robust both at high noise levels and in presence of structured noise such as the one encountered in real LiDAR scans.

Keywords

Point cloud Denoising Graph neural network 

References

  1. 1.
    Alexa, M., Behr, J., Cohen-Or, D., Fleishman, S., Levin, D., Silva, C.T.: Computing and rendering point set surfaces. IEEE Trans. Vis. Comput. Graph. 9(1), 3–15 (2003)CrossRefGoogle Scholar
  2. 2.
    Öztireli, A.C., Guennebaud, G., Gross, M.: Feature preserving point set surfaces based on non-linear kernel regression. In: Computer Graphics Forum, vol. 28, pp. 493–501. Wiley Online Library (2009)Google Scholar
  3. 3.
    Guennebaud, G., Gross, M.: Algebraic point set surfaces. ACM Trans. Graph. (TOG) 26, 23-es (2007)CrossRefGoogle Scholar
  4. 4.
    Lipman, Y., Cohen-Or, D., Levin, D., Tal-Ezer, H.: Parameterization-free projection for geometry reconstruction. ACM Trans. Graph. (TOG) 26, 22-es (2007)CrossRefGoogle Scholar
  5. 5.
    Huang, H., Wu, S., Gong, M., Cohen-Or, D., Ascher, U., Zhang, H.R.: Edge-aware point set resampling. ACM Trans. Graph. (TOG) 32(1), 1–12 (2013). Article no. 9CrossRefGoogle Scholar
  6. 6.
    Cazals, F., Pouget, M.: Estimating differential quantities using polynomial fitting of osculating jets. Comput. Aided Geom. Des. 22(2), 121–146 (2005)MathSciNetCrossRefGoogle Scholar
  7. 7.
    Zhang, K., Zuo, W., Chen, Y., Meng, D., Zhang, L.: Beyond a Gaussian denoiser: residual learning of deep CNN for image denoising. IEEE Trans. Image Process. 26(7), 3142–3155 (2017)MathSciNetCrossRefGoogle Scholar
  8. 8.
    Liu, D., Wen, B., Fan, Y., Loy, C.C., Huang, T.S.: Non-local recurrent network for image restoration. In: Advances in Neural Information Processing Systems, pp. 1673–1682 (2018)Google Scholar
  9. 9.
    Valsesia, D., Fracastoro, G., Magli, E.: Image denoising with graph-convolutional neural networks. In: 2019 IEEE International Conference on Image Processing (ICIP), pp. 2399–2403 (September 2019)Google Scholar
  10. 10.
    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)Google Scholar
  11. 11.
    Bronstein, M.M., Bruna, J., LeCun, Y., Szlam, A., Vandergheynst, P.: Geometric deep learning: going beyond Euclidean data. IEEE Sig. Process. Mag. 34(4), 18–42 (2017)CrossRefGoogle Scholar
  12. 12.
    Simonovsky, M., Komodakis, N.: Dynamic edge-conditioned filters in convolutional neural networks on graphs. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 29–38 (July 2017)Google Scholar
  13. 13.
    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). Article no. 146CrossRefGoogle Scholar
  14. 14.
    Litany, O., Bronstein, A., Bronstein, M., Makadia, A.: Deformable shape completion with graph convolutional autoencoders. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1886–1895 (2018)Google Scholar
  15. 15.
    Valsesia, D., Fracastoro, G., Magli, E.: Learning localized generative models for 3D point clouds via graph convolution. In: International Conference on Learning Representations, ICLR 2019 (2019)Google Scholar
  16. 16.
    Rakotosaona, M.J., La Barbera, V., Guerrero, P., Mitra, N.J., Ovsjanikov, M.: PointCleanNet: learning to denoise and remove outliers from dense point clouds. In: Computer Graphics Forum. Wiley Online Library (2019)Google Scholar
  17. 17.
    Duan, C., Chen, S., Kovacevic, J.: 3D point cloud denoising via deep neural network based local surface estimation. In: 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 8553–8557. IEEE (2019)Google Scholar
  18. 18.
    Avron, H., Sharf, A., Greif, C., Cohen-Or, D.: l1-sparse reconstruction of sharp point set surfaces. ACM Trans. Graph. (TOG) 29(5), 1–12 (2010). Article no. 135CrossRefGoogle Scholar
  19. 19.
    Sun, Y., Schaefer, S., Wang, W.: Denoising point sets via l0 minimization. Comput. Aided Geom. Des. 35, 2–15 (2015)CrossRefGoogle Scholar
  20. 20.
    Mattei, E., Castrodad, A.: Point cloud denoising via moving RPCA. In: Computer Graphics Forum, vol. 36, pp. 123–137. Wiley Online Library (2017)Google Scholar
  21. 21.
    Zeng, J., Cheung, G., Ng, M., Pang, J., Yang, C.: 3D point cloud denoising using graph Laplacian regularization of a low dimensional manifold model. arXiv preprint arXiv:1803.07252 (2018)
  22. 22.
    Dinesh, C., Cheung, G., Bajic, I.V.: 3D Point Cloud Denoising via Bipartite Graph Approximation and Reweighted Graph Laplacian. arXiv preprint arXiv:1812.07711 (2018)
  23. 23.
    Schoenenberger, Y., Paratte, J., Vandergheynst, P.: Graph-based denoising for time-varying point clouds. In: 3DTV-Conference: The True Vision-Capture, Transmission and Display of 3D Video (3DTV-CON), vol. 2015, pp. 1–4. IEEE (2015)Google Scholar
  24. 24.
    Hermosilla, P., Ritschel, T., Ropinski, T.: Total Denoising: Unsupervised Learning of 3D Point Cloud Cleaning. arXiv preprint arXiv:1904.07615 (2019)
  25. 25.
    Roveri, R., Öztireli, A.C., Pandele, I., Gross, M.: PointProNets: consolidation of point clouds with convolutional neural networks. In: Computer Graphics Forum, vol. 37, pp. 87–99. Wiley Online Library (2018)Google Scholar
  26. 26.
    Han, X.F., Jin, J.S., Wang, M.J., Jiang, W., Gao, L., Xiao, L.: A review of algorithms for filtering the 3D point cloud. Sig. Process. Image Commun. 57, 103–112 (2017)CrossRefGoogle Scholar
  27. 27.
    Shuman, D.I., Narang, S.K., Frossard, P., Ortega, A., Vandergheynst, P.: The emerging field of signal processing on graphs: extending high-dimensional data analysis to networks and other irregular domains. IEEE Sig. Process. Mag. 30(3), 83–98 (2013)CrossRefGoogle Scholar
  28. 28.
    Valsesia, D., Fracastoro, G., Magli, E.: Deep Graph-Convolutional Image Denoising. arXiv preprint arXiv:1907.08448 (2019)
  29. 29.
    Hamilton, W., Ying, Z., Leskovec, J.: Inductive representation learning on large graphs. In: Advances in Neural Information Processing Systems, pp. 1024–1034 (2017)Google Scholar
  30. 30.
    Verma, N., Boyer, E., Verbeek, J.: FeaStNet: feature-steered graph convolutions for 3D shape analysis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2598–2606 (2018)Google Scholar
  31. 31.
    Chang, A.X., et al.: ShapeNet: An Information-Rich 3D Model Repository. Technical report. arXiv:1512.03012 [cs.GR], Stanford University – Princeton University – Toyota Technological Institute at Chicago (2015)
  32. 32.
    Cignoni, P., Callieri, M., Corsini, M., Dellepiane, M., Ganovelli, F., Ranzuglia, G.: MeshLab: an open-source mesh processing tool. In: Scarano, V., Chiara, R.D., Erra, U. (eds.) Eurographics Italian Chapter Conference. The Eurographics Association (2008)Google Scholar
  33. 33.
    Burger, H.C., Schuler, C.J., Harmeling, S.: Image denoising: can plain neural networks compete with BM3D? In: IEEE Conference on Computer Vision and Pattern Recognition, vol. 2012, pp. 2392–2399. IEEE (2012)Google Scholar
  34. 34.
    Gschwandtner, M., Kwitt, R., Uhl, A., Pree, W.: BlenSor: blender sensor simulation toolbox. In: Bebis, G., et al. (eds.) ISVC 2011. LNCS, vol. 6939, pp. 199–208. Springer, Heidelberg (2011).  https://doi.org/10.1007/978-3-642-24031-7_20CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Politecnico di TorinoTurinItaly

Personalised recommendations