Abstract
We propose a multi-level critical point aggregation architecture based on a graph attention mechanism for 3D point cloud normal estimation, which can efficiently focus on locally important points during the feature extraction process. Wherein, the local feature aggregation (LFA) module and the global feature refinement (GFR) module are designed to accurately identify critical points which are geometrically closer to tangent plane for surface fitting at both local and global levels. Specifically, the LFA module captures significant local information from neighboring points with strong geometric correlations to the query point in the low-level feature space. The GFR module enhances the exploration of global geometric correlations in the high-level feature space, allowing the network to focus precisely on critical global points. To address indistinguishable features in the low-level space, we implement a stacked LFA structure. This structure transfers essential adjacent information across multiple levels, enabling deep feature aggregation layer by layer. Then the GFR module can leverage robust local geometric information and refines it into comprehensive global features. Our multi-level point-aware architecture improves the stability and accuracy of surface fitting and normal estimation, even in the presence of sharp features, high noise or anisotropic structures. Experimental results demonstrate that our method is competitive and achieves stable performance on both synthetic and real-world datasets. Code is available at https://github.com/CharlesLee96/NormalEstimation.
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00371-024-03532-x/MediaObjects/371_2024_3532_Fig1_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00371-024-03532-x/MediaObjects/371_2024_3532_Fig2_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00371-024-03532-x/MediaObjects/371_2024_3532_Fig3_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00371-024-03532-x/MediaObjects/371_2024_3532_Fig4_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00371-024-03532-x/MediaObjects/371_2024_3532_Fig5_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00371-024-03532-x/MediaObjects/371_2024_3532_Fig6_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00371-024-03532-x/MediaObjects/371_2024_3532_Fig7_HTML.png)
Similar content being viewed by others
Data availability
The training and test data have been deposited in the web of Github: https://github.com/LeoQLi/HSurf-Net, and our code can be obtain at : https://github.com/CharlesLee96/NormalEstimation
References
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)
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)
Stewart, G.W.: On the early history of the singular value decomposition. SIAM Rev. 35(4), 551–566 (1993)
Guerrero, P., Kleiman, Y., Ovsjanikov, M., Mitra, N.J.: Pcpnet learning local shape properties from raw point clouds. In: Computer Graphics Forum, vol. 37, pp. 75–85 (2018). Wiley Online Library
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)
Ben-Shabat, Y., Gould, S.: Deepfit: 3D surface fitting via neural network weighted least squares. In: Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part I 16, pp. 20–34 (2020). Springer
Zhou, J., **, W., Wang, M., Liu, X., Li, Z., Liu, Z.: Improvement of normal estimation for point clouds via simplifying surface fitting. Comput. Aided Des. 161, 103533 (2023)
Li, K., Zhao, M., Wu, H., Yan, D.-M., Shen, Z., Wang, F.-Y., **ong, G.: Graphfit: learning multi-scale graph-convolutional representation for point cloud normal estimation. In: European Conference on Computer Vision, pp. 651–667 (2022). Springer
Li, Q., Liu, Y.-S., Cheng, J.-S., Wang, C., Fang, Y., Han, Z.: Hsurf-net: normal estimation for 3D point clouds by learning hyper surfaces. Adv. Neural. Inf. Process. Syst. 35, 4218–4230 (2022)
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)
Levin, D.: The approximation power of moving least-squares. Math. Comput. 67(224), 1517–1531 (1998)
Guennebaud, G., Gross, M.: Algebraic point set surfaces. In: ACM Siggraph 2007 Papers, p. 23 (2007)
Cazals, F., Pouget, M.: Estimating differential quantities using polynomial fitting of osculating jets. Comput. Aided Geom. Design 22(2), 121–146 (2005)
Mitra, N.J., Nguyen, A.: Estimating surface normals in noisy point cloud data. In: Proceedings of the Nineteenth Annual Symposium on Computational Geometry, pp. 322–328 (2003)
Alliez, P., Cohen-Steiner, D., Tong, Y., Desbrun, M.: Voronoi-based variational reconstruction of unoriented point sets. In: Symposium on Geometry Processing, vol. 7, pp. 39–48 (2007)
Mérigot, Q., Ovsjanikov, M., Guibas, L.J.: Voronoi-based curvature and feature estimation from point clouds. IEEE Trans. Visual Comput. Graph. 17(6), 743–756 (2010)
Boulch, A., Marlet, R.: Fast and robust normal estimation for point clouds with sharp features. In: Computer Graphics Forum, Wiley Online Library, vol. 31, pp. 1765–1774 (2012)
Boulch, A., Marlet, R.: Deep learning for robust normal estimation in unstructured point clouds. In: Computer Graphics Forum, Wiley Online Library, vol. 35, pp. 281–290 (2016)
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)
Zhou, J., Huang, H., Liu, B., Liu, X.: Normal estimation for 3D point clouds via local plane constraint and multi-scale selection. Comput. Aided Des. 129, 102916 (2020)
**u, H., Liu, X., Wang, W., Kim, K.-S., Matsuoka, M.: Msecnet: accurate and robust normal estimation for 3d point clouds by multi-scale edge conditioning. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 2535–2543 (2023)
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)
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)
Zhou, J., **, W., Wang, M., Liu, X., Li, Z., Liu, Z.: Fast and accurate normal estimation for point clouds via patch stitching. Comput. Aided Des. 142, 103121 (2022)
Li, Q., Feng, H., Shi, K., Gao, Y., Fang, Y., Liu, Y.-S., Han, Z.: Shs-net: learning signed hyper surfaces for oriented normal estimation of point clouds. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 13591–13600 (2023)
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, Ł., Polosukhin, I.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30, (2017)
Cao, J., Zhu, H., Bai, Y., Zhou, J., Pan, J., Su, Z.: Latent tangent space representation for normal estimation. IEEE Trans. Ind. Electron. 69(1), 921–929 (2021)
Zhou, H., Chen, H., Zhang, Y., Wei, M., **e, H., Wang, J., Lu, T., Qin, J., Zhang, X.-P.: Refine-net: normal refinement neural network for noisy point clouds. IEEE Trans. Pattern Anal. Mach. Intell. 45(1), 946–963 (2022)
Li, S., Zhou, J., Ma, B., Liu, Y.-S., Han, Z.: Neaf: learning neural angle fields for point normal estimation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37, pp. 1396–1404 (2023)
Hua, B.-S., Pham, Q.-H., Nguyen, D.T., Tran, M.-K., Yu, L.-F., Yeung, S.-K.: Scenenn: a scene meshes dataset with annotations. In: 2016 Fourth International Conference on 3D Vision (3DV), pp. 92–101 (2016). IEEE
Hackel, T., Savinov, N., Ladicky, L., Wegner, J.D., Schindler, K., Pollefeys, M.: Semantic3d. net: a new large-scale point cloud classification benchmark. ar**v preprint ar**v:1704.03847 (2017)
Paszke, A., Gross, S., Chintala, S., Chanan, G.: Pytorch: tensors and dynamic neural networks in python with strong gpu acceleration. PyTorch Tensors Dyn. Neural Netw. Python Strong GPU Accel. 6(3), 67 (2017)
Kazhdan, M., Bolitho, M., Hoppe, H.: Poisson surface reconstruction. In: Proceedings of the Fourth Eurographics Symposium on Geometry Processing, vol. 7, p. 0 (2006)
Acknowledgements
This research was supported in part by the Natural Science Foundation of China under Grants 62002040, in part by China Postdoctoral Science Foundation 2021M690501, in part by the Science Foundation of Zhejiang Sci-Tech University under Grant Number 22062338-Y and in part by Bei**g Postdoctoral Science Foundation under Grant Number 2022-ZZ-069.
Ethics declarations
Conflict of interest
The authors declare no competing interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Zhou, J., Li, Y., Wang, M. et al. Robust point cloud normal estimation via multi-level critical point aggregation. Vis Comput (2024). https://doi.org/10.1007/s00371-024-03532-x
Accepted:
Published:
DOI: https://doi.org/10.1007/s00371-024-03532-x