Skip to main content
Springer Nature Link
Log in

Enhancing Robustness to Noise Corruption for Point Cloud Recognition via Spatial Sorting and Set-Mixing Aggregation Module

  • Conference paper
  • First Online:
Computer Vision – ACCV 2024 (ACCV 2024)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 15480))

Included in the following conference series:

  • 166 Accesses

Abstract

Current models for point cloud recognition demonstrate promising performance on synthetic datasets. However, real-world point cloud data inevitably contains noise, impacting model robustness. While recent efforts focus on enhancing robustness through various strategies, there still remains a gap in comprehensive analyzes from the standpoint of network architecture design. Unlike traditional methods that rely on generic techniques, our approach optimizes model robustness to noise corruption through network architecture design. Inspired by the token-mixing technique applied in 2D images, we propose Set-Mixer, a noise-robust aggregation module which facilitates communication among all points to extract geometric shape information and mitigating the influence of individual noise points. A sorting strategy is designed to enable our module to be invariant to point permutation, which also tackles the unordered structure of point cloud and introduces consistent relative spatial information. Experiments conducted on ModelNet40-C indicate that Set-Mixer significantly enhances the model performance on noisy point clouds, underscoring its potential to advance real-world applicability in 3D recognition and perception tasks.

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

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Bonatto, D., Rogge, S., Schenkel, A., Ercek, R., Lafruit, G.: Explorations for real-time point cloud rendering of natural scenes in virtual reality. In: International Conference on 3D Imaging, (IC3D). pp. 1–7 (2016). https://doi.org/10.1109/IC3D.2016.7823453

  2. Cai, Q., Pan, Y., Yao, T., Mei, T.: 3d cascade RCNN: high quality object detection in point clouds. IEEE Trans. Image Process. 31, 5706–5719 (2022). https://doi.org/10.1109/TIP.2022.3201469

    Article  Google Scholar 

  3. Cao, C., Preda, M., Zaharia, T.B.: 3d point cloud compression: A survey. In: The 24th International Conference on 3D Web Technology, (Web3D). pp. 1–9 (2019). https://doi.org/10.1145/3329714.3338130

  4. Chen, Y., Duan, L., Zhao, S., Ding, C., Tao, D.: Local-consistent transformation learning for rotation-invariant point cloud analysis. CoRR abs/2403.11113 (2024). https://doi.org/10.48550/ARXIV.2403.11113

  5. Chen, Y., Hu, V.T., Gavves, E., Mensink, T., Mettes, P., Yang, P., Snoek, C.G.M.: Pointmixup: Augmentation for point clouds. In: 16th European Conference on Computer Vision, (ECCV). vol. 12348, pp. 330–345 (2020). https://doi.org/10.1007/978-3-030-58580-8_20

  6. Choe, J., Park, C., Rameau, F., Park, J., Kweon, I.S.: Pointmixer: Mlp-mixer for point cloud understanding. In: 17th European Conference on Computer Vision, (ECCV). vol. 13687, pp. 620–640 (2022). https://doi.org/10.1007/978-3-031-19812-0_36

  7. Dong, X., Chen, D., Zhou, H., Hua, G., Zhang, W., Yu, N.: Self-robust 3d point recognition via gather-vector guidance. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, (CVPR). pp. 11513–11521 (2020). https://doi.org/10.1109/CVPR42600.2020.01153

  8. Dong, Y., Kang, C., Zhang, J., Zhu, Z., Wang, Y., Yang, X., Su, H., Wei, X., Zhu, J.: Benchmarking robustness of 3d object detection to common corruptions in autonomous driving. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition, (CVPR). pp. 1022–1032 (2023). https://doi.org/10.1109/CVPR52729.2023.00105

  9. Engel, N., Belagiannis, V., Dietmayer, K.: Point transformer. IEEE Access. 9, 134826–134840 (2021). https://doi.org/10.1109/ACCESS.2021.3116304

    Article  Google Scholar 

  10. Goyal, A., Law, H., Liu, B., Newell, A., Deng, J.: Revisiting point cloud shape classification with a simple and effective baseline. In: International Conference on Machine Learning, (ICML). pp. 3809–3820 (2021)

    Google Scholar 

  11. Guo, M., Cai, J., Liu, Z., Mu, T., Martin, R.R., Hu, S.: PCT: point cloud transformer. Comput. Vis. Media 7(2), 187–199 (2021). https://doi.org/10.1007/S41095-021-0229-5

    Article  Google Scholar 

  12. Jia, D., Hermans, A., Leibe, B.: 2d vs. 3d lidar-based person detection on mobile robots. In: IEEE/RSJ International Conference on Intelligent Robots and Systems, (IROS). pp. 3604–3611 (2022). https://doi.org/10.1109/IROS47612.2022.9981519

  13. Kim, S., Lee, S., Hwang, D., Lee, J., Hwang, S.J., Kim, H.J.: Point cloud augmentation with weighted local transformations. In: IEEE/CVF International Conference on Computer Vision, (ICCV). pp. 528–537 (2021)

    Google Scholar 

  14. Lee, D., Lee, J., Lee, J., Lee, H., Lee, M., Woo, S., Lee, S.: Regularization strategy for point cloud via rigidly mixed sample. In: IEEE Conference on Computer Vision and Pattern Recognition, (CVPR). pp. 15900–15909 (2021). https://doi.org/10.1109/CVPR46437.2021.01564

  15. Levi, M.Y., Gilboa, G.: Epic: Ensemble of partial point clouds for robust classification. In: IEEE/CVF International Conference on Computer Vision, (ICCV). pp. 14429–14438 (2023). https://doi.org/10.1109/ICCV51070.2023.01331

  16. Levi, M.Y., Gilboa, G.: Robustifying point cloud networks by refocusing. CoRR abs/2308.05525 (2024)

    Google Scholar 

  17. Liu, D., Yu, R., Su, H.: Extending adversarial attacks and defenses to deep 3d point cloud classifiers. In: IEEE International Conference on Image Processing, (ICIP). pp. 2279–2283 (2019). https://doi.org/10.1109/ICIP.2019.8803770

  18. Liu, H., Jia, J., Gong, N.Z.: Pointguard: Provably robust 3d point cloud classification. In: Proceedings of the IEEE/CVF conference on Computer Vision and Pattern Recognition, (CVPR). pp. 6186–6195 (2021)

    Google Scholar 

  19. Liu, Y., Fan, B., Xiang, S., Pan, C.: Relation-shape convolutional neural network for point cloud analysis. In: IEEE Conference on Computer Vision and Pattern Recognition, (CVPR). pp. 8895–8904 (2019). https://doi.org/10.1109/CVPR.2019.00910

  20. Ma, X., Qin, C., You, H., Ran, H., Fu, Y.: Rethinking network design and local geometry in point cloud: A simple residual MLP framework. In: The Tenth International Conference on Learning Representations, (ICLR) (2022)

    Google Scholar 

  21. Qi, C.R., Su, H., Mo, K., Guibas, L.J.: Pointnet: Deep learning on point sets for 3d classification and segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition, (CVPR). pp. 77–85 (2017). https://doi.org/10.1109/CVPR.2017.16

  22. 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 30: Annual Conference on Neural Information Processing Systems 2017, (NeurIPS). pp. 5099–5108 (2017)

    Google Scholar 

  23. Ren, J., Pan, L., Liu, Z.: Benchmarking and analyzing point cloud classification under corruptions. In: International Conference on Machine Learning, (ICML). vol. 162, pp. 18559–18575 (2022)

    Google Scholar 

  24. Ren, J., Pan, L., Liu, Z.: Benchmarking and analyzing point cloud classification under corruptions. In: International Conference on Machine Learning, (ICML). Proceedings of Machine Learning Research, vol. 162, pp. 18559–18575 (2022)

    Google Scholar 

  25. Schneider, S., Rusak, E., Eck, L., Bringmann, O., Brendel, W., Bethge, M.: Improving robustness against common corruptions by covariate shift adaptation. In: Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, (NeurIPS) (2020)

    Google Scholar 

  26. Sun, J., Cao, Y., Choy, C.B., Yu, Z., Anandkumar, A., Mao, Z.M., Xiao, C.: Adversarially robust 3d point cloud recognition using self-supervisions. In: Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, (NeurIPS). pp. 15498–15512 (2021)

    Google Scholar 

  27. Sun, J., Zhang, Q., Kailkhura, B., Yu, Z., Xiao, C., Mao, Z.M.: Benchmarking robustness of 3d point cloud recognition against common corruptions. CoRR abs/2201.12296 (2022)

    Google Scholar 

  28. Tolstikhin, I.O., Houlsby, N., Kolesnikov, A., Beyer, L., Zhai, X., Unterthiner, T., Yung, J., Steiner, A., Keysers, D., Uszkoreit, J., Lucic, M., Dosovitskiy, A.: Mlp-mixer: An all-mlp architecture for vision. In: Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, (NeurIPS). pp. 24261–24272 (2021)

    Google Scholar 

  29. Uy, M.A., Pham, Q., Hua, B., Nguyen, D.T., Yeung, S.: Revisiting point cloud classification: A new benchmark dataset and classification model on real-world data. In: IEEE/CVF International Conference on Computer Vision, (ICCV). pp. 1588–1597 (2019). https://doi.org/10.1109/ICCV.2019.00167

  30. Wang, D., Shelhamer, E., Liu, S., Olshausen, B.A., Darrell, T.: Tent: Fully test-time adaptation by entropy minimization. In: 9th International Conference on Learning Representations, (ICLR) (2021)

    Google Scholar 

  31. Wang, H., Shen, H., Zhang, B., Wen, Y., Meng, D.: Generating adversarial point clouds on multi-modal fusion based 3d object detection model. In: Information and Communications Security - 23rd International Conference, (ICICS). vol. 12918, pp. 187–203 (2021)

    Google Scholar 

  32. 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), 146:1–146:12 (2019). 10.1145/3326362

    Google Scholar 

  33. Wolff, K., Kim, C., Zimmer, H., Schroers, C., Botsch, M., Sorkine-Hornung, O., Sorkine-Hornung, A.: Point cloud noise and outlier removal for image-based 3d reconstruction. In: Fourth International Conference on 3D Vision, (3DV). pp. 118–127 (2016). 10.1109/3DV.2016.20

    Google Scholar 

  34. Wu, X., Lao, Y., Jiang, L., Liu, X., Zhao, H.: Point transformer V2: grouped vector attention and partition-based pooling. In: Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, (NeurIPS). pp. 33330–33342 (2022)

    Google Scholar 

  35. Wu, Z., Song, S., Khosla, A., Yu, F., Zhang, L., Tang, X., Xiao, J.: 3d shapenets: A deep representation for volumetric shapes. In: IEEE Conference on Computer Vision and Pattern Recognition, (CVPR). pp. 1912–1920 (2015). 10.1109/CVPR.2015.7298801

    Google Scholar 

  36. Wu, Z., Sun, J., Xiao, C.: CSI: enhancing the robustness of 3d point cloud recognition against corruption. CoRR abs/2310.03360 (2023). 10.48550/ARXIV.2310.03360

    Google Scholar 

  37. Xiang, T., Zhang, C., Song, Y., Yu, J., Cai, W.: Walk in the cloud: Learning curves for point clouds shape analysis. In: IEEE/CVF International Conference on Computer Vision, (ICCV). pp. 895–904 (2021). 10.1109/ICCV48922.2021.00095

    Google Scholar 

  38. Xu, J., Tang, X., Zhu, Y., Sun, J., Pu, S.: Sgmnet: Learning rotation-invariant point cloud representations via sorted gram matrix. In: IEEE/CVF International Conference on Computer Vision, (ICCV). pp. 10448–10457 (2021). 10.1109/ICCV48922.2021.01030

    Google Scholar 

  39. Xu, M., Ding, R., Zhao, H., Qi, X.: Paconv: Position adaptive convolution with dynamic kernel assembling on point clouds. In: IEEE Conference on Computer Vision and Pattern Recognition, (CVPR). pp. 3173–3182 (2021). 10.1109/CVPR46437.2021.00319

    Google Scholar 

  40. Xu, M., Zhang, J., Zhou, Z., Xu, M., Qi, X., Qiao, Y.: Learning geometry-disentangled representation for complementary understanding of 3d object point cloud. In: Thirty-Fifth AAAI Conference on Artificial Intelligence, (AAAI). pp. 3056–3064 (2021). 10.1609/AAAI.V35I4.16414

    Google Scholar 

  41. Yu, J., Zhang, C., Cai, W.: Rethinking rotation invariance with point cloud registration. In: Thirty-Seventh AAAI Conference on Artificial Intelligence, (AAAI). pp. 3313–3321 (2023). 10.1609/AAAI.V37I3.25438

    Google Scholar 

  42. Yu, J., Zhang, C., Wang, H., Zhang, D., Song, Y., Xiang, T., Liu, D., Cai, W.: 3d medical point transformer: Introducing convolution to attention networks for medical point cloud analysis. CoRR abs/2112.04863 (2021)

    Google Scholar 

  43. Zhang, D., Yu, J., Zhang, C., Cai, W.: Parot: Patch-wise rotation-invariant network via feature disentanglement and pose restoration. In: Thirty-Seventh AAAI Conference on Artificial Intelligence, (AAAI). pp. 3418–3426 (2023). 10.1609/AAAI.V37I3.25450

    Google Scholar 

  44. Zhang, J., Chen, L., Ouyang, B., Liu, B., Zhu, J., Chen, Y., Meng, Y., Wu, D.: Pointcutmix: Regularization strategy for point cloud classification. Neurocomputing 505, 58–67 (2022). https://doi.org/10.1016/J.NEUCOM.2022.07.049

    Article  Google Scholar 

  45. Zhang, K., Zhou, H., Zhang, J., Huang, Q., Zhang, W., Yu, N.: Ada3diff: Defending against 3d adversarial point clouds via adaptive diffusion. In: Proceedings of the 31st ACM International Conference on Multimedia, (ACM MM). pp. 8849–8859 (2023)

    Google Scholar 

  46. Zhang, Z., Hua, B., Rosen, D.W., Yeung, S.: Rotation invariant convolutions for 3d point clouds deep learning. In: International Conference on 3D Vision, (3DV). pp. 204–213 (2019). 10.1109/3DV.2019.00031

    Google Scholar 

  47. Zhang, Z., Hua, B., Yeung, S.: Riconv++: Effective rotation invariant convolutions for 3d point clouds deep learning. Int. J. Comput. Vis. 130(5), 1228–1243 (2022). https://doi.org/10.1007/S11263-022-01601-Z

    Article  Google Scholar 

  48. Zhou, H., Chen, K., Zhang, W., Fang, H., Zhou, W., Yu, N.: Dup-net: Denoiser and upsampler network for 3d adversarial point clouds defense. In: IEEE/CVF International Conference on Computer Vision, (ICCV). pp. 1961–1970 (2019). 10.1109/ICCV.2019.00205

    Google Scholar 

  49. Zhou, Y., Tuzel, O.: Voxelnet: End-to-end learning for point cloud based 3d object detection. In: IEEE Conference on Computer Vision and Pattern Recognition, (CVPR). pp. 4490–4499 (2018). 10.1109/CVPR.2018.00472

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. School of Computer Science, University of Sydney, 2006, Sydney, Australia

    Dingxin Zhang, Jianhui Yu, Tengfei Xue, Chaoyi Zhang, Dongnan Liu & Weidong Cai

Authors
  1. Dingxin Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jianhui Yu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Tengfei Xue
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Chaoyi Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Dongnan Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Weidong Cai
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Weidong Cai .

Editor information

Editors and Affiliations

  1. Pohang University of Science and Technology (POSTECH), Pohang, Korea (Republic of)

    Minsu Cho

  2. Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates

    Ivan Laptev

  3. Google, Mountain View, CA, USA

    Du Tran

  4. National University of Singapore, Singapore, Singapore

    Angela Yao

  5. Peking University, Beijing, China

    Hongbin Zha

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 1197 KB)

Rights and permissions

Reprints and permissions

Copyright information

© 2025 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Zhang, D., Yu, J., Xue, T., Zhang, C., Liu, D., Cai, W. (2025). Enhancing Robustness to Noise Corruption for Point Cloud Recognition via Spatial Sorting and Set-Mixing Aggregation Module. In: Cho, M., Laptev, I., Tran, D., Yao, A., Zha, H. (eds) Computer Vision – ACCV 2024. ACCV 2024. Lecture Notes in Computer Science, vol 15480. Springer, Singapore. https://doi.org/10.1007/978-981-96-0969-7_17

Download citation

  • DOI: https://doi.org/10.1007/978-981-96-0969-7_17

  • Published:

  • Publisher Name: Springer, Singapore

  • Print ISBN: 978-981-96-0968-0

  • Online ISBN: 978-981-96-0969-7

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics