Skip to main content
SpringerLink
Log in

GraphFit: Learning Multi-scale Graph-Convolutional Representation for Point Cloud Normal Estimation

  • Conference paper
  • First Online:
Computer Vision – ECCV 2022 (ECCV 2022)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13692))

Included in the following conference series:

Abstract

We propose a precise and efficient normal estimation method that can deal with noise and nonuniform density for unstructured 3D point clouds. Unlike existing approaches that directly take patches and ignore the local neighborhood relationships, which make them susceptible to challenging regions such as sharp edges, we propose to learn graph convolutional feature representation for normal estimation, which emphasizes more local neighborhood geometry and effectively encodes intrinsic relationships. Additionally, we design a novel adaptive module based on the attention mechanism to integrate point features with their neighboring features, hence further enhancing the robustness of the proposed normal estimator against point density variations. To make it more distinguishable, we introduce a multi-scale architecture in the graph block to learn richer geometric features. Our method outperforms competitors with the state-of-the-art accuracy on various benchmark datasets, and is quite robust against noise, outliers, as well as the density variations. The code is available at https://github.com/UestcJay/GraphFit.

K. Li and M. Zhao—The authors contribute equally in this work.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 89.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 119.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Alliez, P., Cohen-Steiner, D., Tong, Y., Desbrun, M.: Voronoi-based variational reconstruction of unoriented point sets. In: Proceedings of the 5th Eurographics Symposium on Geometry Processing, pp. 39–48 (2007)

    Google Scholar 

  2. Amenta, N., Bern, M.: Surface reconstruction by voronoi filtering. Discrete Comput. Geom. 22(4), 481–504 (1999)

    Article  MathSciNet  MATH  Google Scholar 

  3. Ben-Shabat, Y., Gould, S.: DeepFit: 3D surface fitting via neural network weighted least squares. In: Proceedings of the European Conference on Computer Vision, pp. 20–34 (2020)

    Google Scholar 

  4. Ben-Shabat, Y., Lindenbaum, M., Fischer, A.: 3DMFV: three-dimensional point cloud classification in real-time using convolutional neural networks. IEEE Robot. Autom. Lett. 3(4), 3145–3152 (2018)

    Article  Google Scholar 

  5. Ben-Shabat, Y., Lindenbaum, M., Fischer, A.: Nesti-Net: Normal estimation for unstructured 3D point clouds using convolutional neural networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10112–10120 (2019)

    Google Scholar 

  6. Boulch, A., Marlet, R.: Fast and robust normal estimation for point clouds with sharp features. Comput. Graph. Forum. 31(5), 1765–1774 (2012)

    Article  Google Scholar 

  7. Boulch, A., Marlet, R.: Deep learning for robust normal estimation in unstructured point clouds. Comput. Graph. Forum 35(5), 281–290 (2016)

    Article  Google Scholar 

  8. Castillo, E., Liang, J., Zhao, H.: Point cloud segmentation and denoising via constrained nonlinear least squares normal estimates, pp. 283–299 (2013)

    Google Scholar 

  9. Cazals, F., Pouget, M.: Estimating differential quantities using polynomial fitting of osculating jets. Comput. Aided Geom. Des. 22(2), 121–146 (2005)

    Article  MathSciNet  MATH  Google Scholar 

  10. Che, E., Olsen, M.J.: Multi-scan segmentation of terrestrial laser scanning data based on normal variation analysis. ISPRS J. Photogramm. Remote. Sens. 143, 233–248 (2018)

    Article  Google Scholar 

  11. Comino, M., Andujar, C., Chica, A., Brunet, P.: Sensor-aware normal estimation for point clouds from 3D range scans. Comput. Graph. Forum 37(5), 233–243 (2018)

    Article  Google Scholar 

  12. Dey, T.K., Goswami, S.: Provable surface reconstruction from noisy samples. Comput. Geom. 35(1–2), 124–141 (2006)

    Article  MathSciNet  MATH  Google Scholar 

  13. Fan, S., Dong, Q., Zhu, F., Lv, Y., Ye, P., Wang, F.Y.: SCF-Net: learning spatial contextual features for large-scale point cloud segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 14504–14513 (2021)

    Google Scholar 

  14. Fleishman, S., Cohen-Or, D., Silva, C.T.: Robust moving least-squares fitting with sharp features. ACM Trans. Graph. 24(3), 544–552 (2005)

    Article  Google Scholar 

  15. Giraudot, S., Cohen-Steiner, D., Alliez, P.: Noise-adaptive shape reconstruction from raw point sets. Comput. Graph. Forum 32(5), 229–238 (2013)

    Article  MATH  Google Scholar 

  16. Guennebaud, G., Gross, M.: Algebraic point set surfaces. ACM Trans. Graph. 26, 23-es (2007)

    Google Scholar 

  17. Guerrero, P., Kleiman, Y., Ovsjanikov, M., Mitra, N.J.: Pcpnet learning local shape properties from raw point clouds. Comput. Graph. Forum. 37(2), 75–85 (2018)

    Article  Google Scholar 

  18. Hashimoto, T., Saito, M.: Normal estimation for accurate 3D mesh reconstruction with point cloud model incorporating spatial structure. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 54–63 (2019)

    Google Scholar 

  19. Hermosilla, P., Ritschel, T., Ropinski, T.: Total denoising: Unsupervised learning of 3D point cloud cleaning. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 52–60 (2019)

    Google Scholar 

  20. Hoppe, H., DeRose, T., Duchamp, T., McDonald, J., Stuetzle, W.: Surface reconstruction from unorganized points. In: Proceedings of the 19th Annual Conference on Computer Graphics and Interactive Techniques, pp. 71–78 (1992)

    Google Scholar 

  21. Hu, J., Shen, L., Sun, G.: Squeeze-and-Excitation networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7132–7141 (2018)

    Google Scholar 

  22. Hua, B.S., Tran, M.K., Yeung, S.K.: Pointwise convolutional neural networks. In: Proceedings of the IEEE/CVF conference on Computer Vision and Pattern Recognition, pp. 984–993 (2018)

    Google Scholar 

  23. Kazhdan, M., Bolitho, M., Hoppe, H.: Poisson surface reconstruction. In: Proceedings of the 4th Eurographics Symposium on Geometry Processing, vol. 7 (2006)

    Google Scholar 

  24. Khaloo, A., Lattanzi, D.: Robust normal estimation and region growing segmentation of infrastructure 3D point cloud models. Adv. Eng. Inform. 34, 1–16 (2017)

    Article  Google Scholar 

  25. Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Proceedings of the International Conference on Learning Representations (2015)

    Google Scholar 

  26. Lenssen, J.E., Osendorfer, C., Masci, J.: Deep iterative surface normal estimation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 11247–11256 (2020)

    Google Scholar 

  27. Levin, D.: The approximation power of moving least-squares. Math. Comput. 67(224), 1517–1531 (1998)

    Article  MathSciNet  MATH  Google Scholar 

  28. Lu, D., Lu, X., Sun, Y., Wang, J.: Deep feature-preserving normal estimation for point cloud filtering. Comput. Aided Des. 125, 102860 (2020)

    Article  MathSciNet  Google Scholar 

  29. Lu, X., Schaefer, S., Luo, J., Ma, L., He, Y.: Low rank matrix approximation for 3D geometry filtering. IEEE Trans. Visual Comput. Graphics 28(04), 1835–1847 (2022)

    Article  Google Scholar 

  30. Mérigot, Q., Ovsjanikov, M., Guibas, L.J.: Voronoi-based curvature and feature estimation from point clouds. IEEE Trans. Visual Comput. Graphics 17(6), 743–756 (2010)

    Article  Google Scholar 

  31. Mitra, N.J., Nguyen, A.: Estimating surface normals in noisy point cloud data. In: Proceedings of the 19th Annual Symposium on Computational Geometry, pp. 322–328 (2003)

    Google Scholar 

  32. Nurunnabi, A., Belton, D., West, G.: Robust statistical approaches for local planar surface fitting in 3D laser scanning data. ISPRS J. Photogramm. Remote. Sens. 96, 106–122 (2014)

    Article  Google Scholar 

  33. Nurunnabi, A., West, G., Belton, D.: Outlier detection and robust normal-curvature estimation in mobile laser scanning 3D point cloud data. Pattern Recogn. 48(4), 1404–1419 (2015)

    Article  Google Scholar 

  34. Pistilli, F., Fracastoro, G., Valsesia, D., Magli, E.: Learning graph-convolutional representations for point cloud denoising. In: Proceedings of the European Conference on Computer Vision, pp. 103–118 (2020)

    Google Scholar 

  35. 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/CVF Conference on Computer Vision and Pattern Recognition, pp. 652–660 (2017)

    Google Scholar 

  36. Qi, C.R., Yi, L., Su, H., Guibas, L.J.: PointNet++: deep hierarchical feature learning on point sets in a metric space, pp. 5100–5109 (2017)

    Google Scholar 

  37. Rakotosaona, M.J., La Barbera, V., Guerrero, P., Mitra, N.J., Ovsjanikov, M.: PointCleanNet: learning to denoise and remove outliers from dense point clouds. Comput. Graph. Forum. 39(1), 185–203 (2020)

    Article  Google Scholar 

  38. Silberman, N., Hoiem, D., Kohli, P., Fergus, R.: Indoor segmentation and support inference from rgbd images. In: Proceedings of the European Conference on Computer Vision, pp. 746–760 (2012)

    Google Scholar 

  39. 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(5), 1–12 (2019)

    Article  Google Scholar 

  40. Wang, Z., Prisacariu, V.A.: Neighbourhood-insensitive point cloud normal estimation network (2020)

    Google Scholar 

  41. Yu, L., Li, X., Fu, C.-W., Cohen-Or, D., Heng, P.-A.: EC-net: an edge-aware point set consolidation network. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 398–414. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01234-2_24

    Chapter  Google Scholar 

  42. Zhang, D., Lu, X., Qin, H., He, Y.: PointFilter: point cloud filtering via encoder-decoder modeling. IEEE Trans. Visual Comput. Graphics 27(3), 2015–2027 (2020)

    Article  Google Scholar 

  43. Zhang, J., Cao, J.J., Zhu, H.R., Yan, D.M., Liu, X.P.: Geometry guided deep surface normal estimation. Comput. Aided Des. 142, 103119 (2022)

    Article  MathSciNet  Google Scholar 

  44. Zhou, H., et al.: Geometry and learning co-supported normal estimation for unstructured point cloud. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 13238–13247 (2020)

    Google Scholar 

  45. Zhu, R., Liu, Y., Dong, Z., Wang, Y., Jiang, T., Wang, W., Yang, B.: AdaFit: rethinking learning-based normal estimation on point clouds. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 6118–6127 (2021)

    Google Scholar 

Download references

Acknowledgement

This work was supported in part by National Natural Science Foundation of China under Grants 62172415, 61872365, U1909204, U19B2029; Chinese Guangdong’s S &T project under Grant 2019B1515120030, 2021B1515140034; Ministry of Industry and Information Technology Project (TC200802B). CAS Key Technology Talent Program (Zhen Shen), the Tencent AI Laboratory Rhino-Bird Focused Research Program under Grant JR202127 (Dong-Ming Yan), and the Alibaba Group through Alibaba Innovative Research Program.

Author information

Authors and Affiliations

  1. SKLMCCS/NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China

    Keqiang Li, Mingyang Zhao, Huaiyu Wu, Dong-Ming Yan, Zhen Shen, Fei-Yue Wang & Gang Xiong

  2. Beijing Academy of Artificial Intelligence, Beijing, China

    Mingyang Zhao

  3. School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China

    Keqiang Li & Dong-Ming Yan

Authors
  1. Keqiang Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Mingyang Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Huaiyu Wu
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Dong-Ming Yan
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Zhen Shen
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Fei-Yue Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Gang Xiong
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Huaiyu Wu .

Editor information

Editors and Affiliations

  1. Tel Aviv University, Tel Aviv, Israel

    Shai Avidan

  2. University College London, London, UK

    Gabriel Brostow

  3. Google AI, Accra, Ghana

    Moustapha Cissé

  4. University of Catania, Catania, Italy

    Giovanni Maria Farinella

  5. Facebook (United States), Menlo Park, CA, USA

    Tal Hassner

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 20085 KB)

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Li, K. et al. (2022). GraphFit: Learning Multi-scale Graph-Convolutional Representation for Point Cloud Normal Estimation. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol 13692. Springer, Cham. https://doi.org/10.1007/978-3-031-19824-3_38

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-19824-3_38

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-19823-6

  • Online ISBN: 978-3-031-19824-3

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation