Skip to main content

Advertisement

Springer Nature Link
Log in

Mdcsnet: multi-scale dynamic spatial information fusion with criticality sampling for point cloud classification

  • Published:
The Journal of Supercomputing Aims and scope Submit manuscript

Abstract

Point cloud classification is crucial in the processing and analysis of three-dimensional data. However, the irregularities and disorders inherent in point cloud data pose significant challenges when representing point cloud information. Most existing models utilize farthest point sampling to extract subsets of point clouds. However, this method tends to select spatially distant points, which may result in insufficient sampling in regions with high-density variation, leading to the loss of crucial geometric information. To address this issue, we design a hybrid model called MDCSNet, comprising two branches: a farthest point sampling branch and a criticality point sampling branch. The former enhances the perceptual capability of the model by dynamically integrating multi-scale spatial information based on a hierarchical structure. At the same time, the latter employs an optimized criticality point strategy to refine the extraction of crucial features in three-dimensional space. We conducted experiments on various datasets, achieving an overall accuracy of 93.4% and a mean accuracy of 91.8% on the ModelNet40 dataset, and an overall accuracy of 81.82% on the ScanObjectNN dataset, thereby demonstrating the effectiveness of our model.

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

Access this article

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

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

Data Availability

These data are derived from the following resources available in the public domain: https://modelnet.cs.princeton.edu/,https://hkustvgd.github.io/scanobjectnn/.

References

  1. Park J, Kim C, Kim S, Jo K (2023) Pcscnet: Fast 3d semantic segmentation of lidar point cloud for autonomous car using point convolution and sparse convolution network. Expert Systems with Applications 212:118815

    Article  MATH  Google Scholar 

  2. Wang G, Yu L, Tian S, Zhang H, Xue Y, Sang M, Guo J, Yu X, Si S (2024) Pctn: Point cloud data transformation network. Displays 81:102610

    Article  Google Scholar 

  3. Wang C, Ning X, Sun L, Zhang L, Li W, Bai X (2022) Learning discriminative features by covering local geometric space for point cloud analysis. IEEE Transactions on Geoscience and Remote Sensing 60:1–15

    MATH  Google Scholar 

  4. Qi CR, Su H, Nießner M, Dai A, Yan M, Guibas LJ (2016) Volumetric and multi-view cnns for object classification on 3d data. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5648–5656

  5. Su H, Maji S, Kalogerakis E, Learned-Miller E (2015) Multi-view convolutional neural networks for 3d shape recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 945–953

  6. Riegler G, Osman Ulusoy A, Geiger A (2017) Octnet: Learning deep 3d representations at high resolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3577–3586

  7. Maturana D, Scherer S (2015) Voxnet: A 3d convolutional neural network for real-time object recognition. In: 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 922–928. IEEE

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

  9. Qi CR, Su H, Mo K, Guibas LJ (2017) 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

  10. Qi CR, Yi L, Su H, Guibas LJ (2017) Pointnet++: Deep hierarchical feature learning on point sets in a metric space. Advances in neural information processing systems 30

  11. Wang Y, Sun Y, Liu Z, Sarma SE, Bronstein MM, Solomon JM (2019) Dynamic graph cnn for learning on point clouds. ACM Transactions on Graphics (tog) 38(5):1–12

    Article  MATH  Google Scholar 

  12. Turgut K, Dutagaci H (2024) Local region-learning modules for point cloud classification. Machine Vision and Applications 35(1):16

    Article  MATH  Google Scholar 

  13. Lu D, Xie Q, Gao K, Xu L, Li J (2022) 3dctn: 3d convolution-transformer network for point cloud classification. IEEE Transactions on Intelligent Transportation Systems 23(12):24854–24865

    Article  Google Scholar 

  14. Hu Q, Yang B, Xie L, Rosa S, Guo Y, Wang Z, Trigoni N, Markham A (2020) Randla-net: Efficient semantic segmentation of large-scale point clouds. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 11108–11117

  15. Hu Q, Yang B, Xie L, Rosa S, Guo Y, Wang Z, Trigoni N, Markham A (2021) Learning semantic segmentation of large-scale point clouds with random sampling. IEEE Transactions on Pattern Analysis and Machine Intelligence 44(11):8338–8354

    MATH  Google Scholar 

  16. Canny J (1986) A computational approach to edge detection. IEEE Transactions on pattern analysis and machine intelligence 6:679–698

    Article  MATH  Google Scholar 

  17. Ma X, Qin C, You H, Ran H, Fu Y (2022) Rethinking network design and local geometry in point cloud: A simple residual mlp framework. arXiv preprint arXiv:2202.07123

  18. Qian G, Li Y, Peng H, Mai J, Hammoud H, Elhoseiny M, Ghanem B (2022) Pointnext: Revisiting pointnet++ with improved training and scaling strategies. Advances in neural information processing systems 35:23192–23204

    Google Scholar 

  19. Xu M, Zhang J, Zhou Z, Xu M, Qi X, Qiao Y (2021) Learning geometry-disentangled representation for complementary understanding of 3d object point cloud. Proceedings of the AAAI Conference on Artificial Intelligence 35:3056–3064

    Article  MATH  Google Scholar 

  20. Chen X, Wu Y, Xu W, Li J, Dong H, Chen Y (2021) Pointscnet: Point cloud structure and correlation learning based on space-filling curve-guided sampling. Symmetry 14(1):8

    Article  MATH  Google Scholar 

  21. Chen B, Xia Y, Zang Y, Wang C, Li J (2023) Decoupled local aggregation for point cloud learning. arXiv preprint arXiv:2308.16532

  22. Ran H, Liu J, Wang C (2022) Surface representation for point clouds. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 18942–18952

  23. Atzmon M, Maron H, Lipman Y (2018) Point convolutional neural networks by extension operators. arXiv preprint arXiv:1803.10091

  24. Liu Y, Fan B, Xiang S, Pan C (2019) Relation-shape convolutional neural network for point cloud analysis. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8895–8904

  25. Wang Z, Zhang L, Zhang L, Li R, Zheng Y, Zhu Z (2018) A deep neural network with spatial pooling (dnnsp) for 3-d point cloud classification. IEEE Transactions on Geoscience and Remote Sensing 56(8):4594–4604

    Article  MATH  Google Scholar 

  26. Li Y, Bu R, Sun M, Wu W, Di X, Chen B (2018) Pointcnn: Convolution on x-transformed points. Advances in neural information processing systems 31

  27. Qiu S, Anwar S, Barnes N (2021) Geometric back-projection network for point cloud classification. IEEE Transactions on Multimedia 24:1943–1955

    Article  MATH  Google Scholar 

  28. Wu J, Sun M, Jiang C, Liu J, Smith J, Zhang Q (2024) Context-based local-global fusion network for 3d point cloud classification and segmentation. Expert Systems with Applications 251:124023

    Article  Google Scholar 

  29. Thomas H, Qi CR, Deschaud J-E, Marcotegui B, Goulette F, Guibas LJ (2019) Kpconv: Flexible and deformable convolution for point clouds. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 6411–6420

  30. Xu Y, Fan T, Xu M, Zeng L, Qiao Y (2018) Spidercnn: Deep learning on point sets with parameterized convolutional filters. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 87–102

  31. Simonovsky M, Komodakis N (2017) Dynamic edge-conditioned filters in convolutional neural networks on graphs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3693–3702

  32. Mohammadi SS, Wang Y, Del Bue A (2021) Pointview-gcn: 3d shape classification with multi-view point clouds. In: 2021 IEEE International Conference on Image Processing (ICIP), pp. 3103–3107. IEEE

  33. Zhang K, Hao M, Wang J, Silva C, Fu C (2019) Linked dynamic graph cnn: Learning on point cloud via linking hierarchical features. arxiv 2019. arXiv preprint arXiv:1904.10014

  34. Yue C, Wang Y, Tang X, Chen Q (2022) Drgcnn: Dynamic region graph convolutional neural network for point clouds. Expert Systems with Applications 205:117663

    Article  MATH  Google Scholar 

  35. Esteves C, Allen-Blanchette C, Makadia A, Daniilidis K (2018) Learning so (3) equivariant representations with spherical cnns. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 52–68

  36. Zhang Z, Yang L, Xiang Z (2025) Risurconv: Rotation invariant surface attention-augmented convolutions for 3d point cloud classification and segmentation. In: European Conference on Computer Vision, pp. 93–109. Springer

  37. Yang J, Zhang Q, Ni B, Li L, Liu J, Zhou M, Tian Q (2019) Modeling point clouds with self-attention and gumbel subset sampling. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3323–3332

  38. Chen L-Z, Li X-Y, Fan D-P, Wang K, Lu S-P, Cheng M-M (2019) Lsanet: Feature learning on point sets by local spatial aware layer. arXiv preprint arXiv:1905.05442

  39. Chen C, Fragonara LZ, Tsourdos A (2021) Gapointnet: Graph attention based point neural network for exploiting local feature of point cloud. Neurocomputing 438:122–132

    Article  Google Scholar 

  40. Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly S et al (2020) An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929

  41. Guo M-H, Cai J-X, Liu Z-N, Mu T-J, Martin RR, Hu S-M (2021) Pct: Point cloud transformer. Computational Visual Media 7:187–199

    Article  Google Scholar 

  42. Han X-F, He Z-Y, Chen J, Xiao G-Q (2022) 3crossnet: Cross-level cross-scale cross-attention network for point cloud representation. IEEE Robotics and Automation Letters 7(2):3718–3725

    Article  MATH  Google Scholar 

  43. Berg A, Oskarsson M, O’Connor M (2022) Points to patches: Enabling the use of self-attention for 3d shape recognition. In: 2022 26th International Conference on Pattern Recognition (ICPR), pp. 528–534. IEEE

  44. Wu X, Lao Y, Jiang L, Liu X, Zhao H (2022) Point transformer v2: Grouped vector attention and partition-based pooling. Adv in Neural Information Processing Sys 35:33330–33342

    Google Scholar 

  45. Leng, Z, Sun P, He T, Anguelov D, Tan M (2024) Pvtransformer: Point-to-voxel transformer for scalable 3d object detection. arXiv preprint arXiv:2405.02811

  46. Wu X, Jiang L, Wang P-S, Liu Z, Liu X, Qiao Y, Ouyang W, He T, Zhao H (2024) Point transformer v3: Simpler faster stronger. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4840–4851

  47. Kaul C, Pears N, Manandhar S (2021) Fatnet: A feature-attentive network for 3d point cloud processing. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 7211–7218. IEEE

  48. Qiu S, Anwar S, Barnes N (2021) Dense-resolution network for point cloud classification and segmentation. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 3813–3822

  49. Liu X, Han Z, Liu Y-S, Zwicker M (2019) Point2sequence: Learning the shape representation of 3d point clouds with an attention-based sequence to sequence network. In: Proceedings of the AAAI Conference on Artificial Intelligence 33:8778–8785

    MATH  Google Scholar 

  50. Qiu Z, Li Y, Wang Y, Pan Y, Yao T, Mei T (2022) Spe-net: Boosting point cloud analysis via rotation robustness enhancement. In: European Conference on Computer Vision, pp. 593–609. Springer

  51. Li M, Hsu W, Xie X, Cong J, Gao W (2020) Sacnn: Self-attention convolutional neural network for low-dose ct denoising with self-supervised perceptual loss network. IEEE transactions on medical imaging 39(7):2289–2301

    Article  Google Scholar 

  52. Li X, Wei M, Chen S (2023) Pointsmile: Point self-supervised learning via curriculum mutual information. arXiv preprint arXiv:2301.12744

  53. Zhao W, Jia L, Zhai H, Chai S, Li P (2024) Pointsgln: a novel point cloud classification network based on sampling grouping and local point normalization. Multimedia Sys 30(2):106

    Article  MATH  Google Scholar 

  54. Cao X, Xia H, Han X, Wang Y, Li K, Su L (2023) Pointjem: self-supervised point cloud understanding for reducing feature redundancy via joint entropy maximization. arXiv preprint arXiv:2312.03339

  55. Zhang H, Wang C, Yu L, Tian S, Ning X, Rodrigues J (2024) Pointgt: A method for point-cloud classification and segmentation based on local geometric transformation. IEEE Transactions on Multimedia

  56. Zhao H, Jiang L, Jia J, Torr PH, Koltun V (2021) Point transformer. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 16259–16268

  57. Mazur K, Lempitsky V (2021) Cloud transformers: A universal approach to point cloud processing tasks. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 10715–10724

  58. Liu Y, Tian B, Lv Y, Li L, Wang F-Y (2023) Point cloud classification using content-based transformer via clustering in feature space. IEEE/CAA J Automatica Sinica 11(1):231–239

    Article  MATH  Google Scholar 

  59. Zhou W, Zhao Y, Xiao Y, Min X, Yi J (2024) Tnpc: Transformer-based network for point cloud classification. Expert Systems with Applications 239:122438

    Article  Google Scholar 

  60. Liu H, Tian S (2024) Deep 3d point cloud classification and segmentation network base on gatenet. The Visual Computer 40:971–981

    Article  MATH  Google Scholar 

  61. Yue Y, Li X, Peng Y A (2024) 3d point cloud classification method based on adaptive graph convolution and global attention. Sensors 24(2)

  62. Li J, Wang J, Xu T (2024) Pointgl: A simple global-local framework for efficient point cloud analysis. IEEE Transactions on Multimedia 26:6931–6942

    Article  MATH  Google Scholar 

  63. Uy MA, Pham Q-H, Hua B-S, Nguyen T Yeung S-K (2019) Revisiting point cloud classification: A new benchmark dataset and classification model on real-world data. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 1588–1597

  64. Brock A, Lim T, Ritchie JM, Weston N (2016) Generative and discriminative voxel modeling with convolutional neural networks. arXiv preprint arXiv:1608.04236

  65. Shen Y, Feng C, Yang Y, Tian D (2018) Mining point cloud local structures by kernel correlation and graph pooling. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4548–4557

  66. Yavartanoo M, Hung S-H, Neshatavar R, Zhang Y, Lee KM (2021) Polynet: Polynomial neural network for 3d shape recognition with polyshape representation. In: 2021 International Conference on 3D Vision (3DV), pp. 1014–1023. IEEE

Download references

Funding

Tianshan Talent Training Program 2023TSYCLJ0023

National Natural Science Foundation of China under Grant U2003208.

Author information

Author notes

  1. Pusen Xia, Shengwei Tian, Long Yu, Xin Fan, Zhezhe Zhu, Hualong Dong, Na Qu, Tong Liu,and Xiao Yuan contributed equally to this work.

Authors and Affiliations

  1. College of Software, Xinjiang University, NorthWest Road, Urumqi, 830091, Xinjiang, China

    Pusen Xia, Shengwei Tian, Xin Fan, Zhezhe Zhu, Hualong Dong, Na Qu, Tong Liu & Xiao Yuan

  2. Network Center, Xinjiang University, Victory Road, Urumqi, 830091, Xinjiang, China

    Long Yu

Authors
  1. Pusen Xia
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Shengwei Tian
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Long Yu
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Xin Fan
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Zhezhe Zhu
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Hualong Dong
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Na Qu
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Tong Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Xiao Yuan
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Pusen Xia helped in conceptualization, methodology, investigation, formal analysis, writing—original draft, writing, and investigation. Shengwei Tian helped in conceptualization, resources, supervision, and writing. Long Yu helped in visualization and investigation. Xin Fan helped in resources and supervision. Zhezhe Zhu worked in software and validation. Hualong Dong helped in data curation. Na Qu helped in resources. Tong Liu helped in validation. Xiao Yuan helped in results analysis.

Corresponding author

Correspondence to Shengwei Tian.

Ethics declarations

Conflict of interest

All authors declare that they have no conflict of interest.

Ethics approval and consent to participate

Not applicable.

Consent for publication

Not applicable.

Materials availability

Not applicable.

Code availability

We will launch our code on GitHub soon.

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.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Xia, P., Tian, S., Yu, L. et al. Mdcsnet: multi-scale dynamic spatial information fusion with criticality sampling for point cloud classification. J Supercomput 81, 387 (2025). https://doi.org/10.1007/s11227-024-06838-8

Download citation

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s11227-024-06838-8

Keywords