Skip to main content
Log in

EdgeFormer: local patch-based edge detection transformer on point clouds

  • Original Article
  • Published:
Pattern Analysis and Applications Aims and scope Submit manuscript

Abstract

Edge points on 3D point clouds can clearly convey 3D geometry and surface characteristics, therefore, edge detection is widely used in many vision applications with high industrial and commercial demands. However, the fine-grained edge features are difficult to detect effectively as they are generally densely distributed or exhibit small-scale surface gradients. To address this issue, we present a learning-based edge detection network, named EdgeFormer, which mainly consists of two stages. Based on the observation that spatially neighboring points tend to exhibit high correlation, forming the local underlying surface, we convert the edge detection of the entire point cloud into a point classification based on local patches. Therefore, in the first stage, we construct local patch feature descriptors that describe the local neighborhood around each point. In the second stage, we classify each point by analyzing the local patch feature descriptors generated in the first stage. Due to the conversion of the point cloud into local patches, the proposed method can effectively extract the finer details. The experimental results show that our model demonstrates competitive performance compared to six baselines.

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

Access this article

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.

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 and code availability

Publicly available data are used. The datasets are available at https://deep-geometry.github.io/abc-dataset/ and https://www.shapenet.org/download/parts. The code is available at https://github.com/Xieyifei1229/EdgeFormer.

References

  1. Qi CR, Su H, Mo K et al (2017) Pointnet: deep learning on point sets for 3D classification and segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

  2. Guo MH, Cai JX, Liu ZN et al (2021) Pct: point cloud transformer. Comput Vis Media 7:187–199. https://doi.org/10.1007/s41095-021-0229-5

    Article  MATH  Google Scholar 

  3. Tang L, Zhan Y, Chen Z et al (2022) Contrastive boundary learning for point cloud segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 8489–8499

  4. Feng M, Gilani SZ, Wang Y et al (2021) Relation graph network for 3d object detection in point clouds. IEEE Trans Image Process 30:92–107. https://doi.org/10.1109/TIP.2020.3031371

    Article  MATH  Google Scholar 

  5. Wang L, Wang F, Yan F et al (2018) Saliency-guide simplification for point-cloud geometry. In: Proceedings of the International Conference on Machine Vision and Applications. Association for Computing Machinery, New York, NY, USA, ICMVA 2018, pp 36–40. https://doi.org/10.1145/3220511.3220523

  6. Zhang L, Sun Q, He Y (2014) Splatting lines: an efficient method for illustrating 3d surfaces and volumes. In: Proceedings of the 18th Meeting of the ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games. Association for Computing Machinery, New York, NY, USA, I3D ’14, pp 135–142. https://doi.org/10.1145/2556700.2556703

  7. Metzer G, Hanocka R, Giryes R et al (2021) Self-sampling for neural point cloud consolidation. ACM Trans Graph. https://doi.org/10.1145/3470645

    Article  MATH  Google Scholar 

  8. Pauly M, Keiser R, Gross M (2003) Multi-scale feature extraction on point-sampled surfaces. Comput Graph Forum 22(3):281–289. https://doi.org/10.1111/1467-8659.00675

    Article  MATH  Google Scholar 

  9. Xia S, Wang R (2017) A fast edge extraction method for mobile lidar point clouds. IEEE Geosci Remote Sens Lett 14(8):1288–1292. https://doi.org/10.1109/LGRS.2017.2707467

    Article  MATH  Google Scholar 

  10. Guo B, Zhang Y, Gao J et al (2022) Sglbp: subgraph-based local binary patterns for feature extraction on point clouds. Comput Graph Forum 41(6):51–66. https://doi.org/10.1111/cgf.14500

    Article  MATH  Google Scholar 

  11. Daniels J II, Ochotta T, Ha LK et al (2008) Spline-based feature curves from point-sampled geometry. Vis Comput 24(6):449–462. https://doi.org/10.1007/s00371-008-0223-2

    Article  MATH  Google Scholar 

  12. Yu L, Li X, Fu CW et al (2018) Ec-net: an edge-aware point set consolidation network. In: Computer Vision - ECCV 2018: 15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings, Part VII. Springer-Verlag, Berlin, Heidelberg, pp 398–414. https://doi.org/10.1007/978-3-030-01234-2_24

  13. Wang X, Xu Y, Xu K et al (2020) Pie-net: parametric inference of point cloud edges. In: Proceedings of the 34th International Conference on Neural Information Processing Systems. Curran Associates Inc., Red Hook, NY, USA, NIPS’20

  14. Zhu X, Du D, Chen W et al (2023) Nerve: neural volumetric edges for parametric curve extraction from point cloud. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 13601–13610

  15. Rusu RB, Cousins S (2011) 3D is here: point cloud library (pcl). In: 2011 IEEE International Conference on Robotics and Automation. IEEE, Shanghai, China, pp 1–4. https://doi.org/10.1109/ICRA.2011.5980567

  16. Zhang Y, Geng G, Wei X et al (2016) A statistical approach for extraction of feature lines from point clouds. Comput Graph 56:31–45. https://doi.org/10.1016/j.cag.2016.01.004

    Article  MATH  Google Scholar 

  17. Mo K, Zhu S, Chang AX et al (2019) Partnet: a large-scale benchmark for fine-grained and hierarchical part-level 3d object understanding. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

  18. Mérigot Q, Ovsjanikov M, Guibas LJ (2011) Voronoi-based curvature and feature estimation from point clouds. IEEE Trans Vis Comput Graph 17(6):743–756. https://doi.org/10.1109/TVCG.2010.261

    Article  MATH  Google Scholar 

  19. Demarsin K, Vanderstraeten D, Volodine T et al (2007) Detection of closed sharp edges in point clouds using normal estimation and graph theory. Comput Aided Des 39(4):276–283. https://doi.org/10.1016/j.cad.2006.12.005

    Article  MATH  Google Scholar 

  20. Bazazian D, Casas JR, Ruiz-Hidalgo J (2015) Fast and robust edge extraction in unorganized point clouds. In: 2015 International Conference on Digital Image Computing: Techniques and Applications (DICTA). IEEE, Adelaide, Australia, pp 1–8. https://doi.org/10.1109/DICTA.2015.7371262

  21. Gumhold S, Wang X, MacLeod R (2001) Feature extraction from point clouds. In: Proceedings of the 10th international meshing roundtable, pp 293–305

  22. Weber C, Hahmann S, Hagen H (2010) Sharp feature detection in point clouds. In: Proceedings of the 2010 Shape Modeling International Conference. IEEE Computer Society, USA, SMI ’10, pp 175–186. https://doi.org/10.1109/SMI.2010.32

  23. Chen H, Huang Y, Xie Q et al (2022) Multiscale feature line extraction from raw point clouds based on local surface variation and anisotropic contraction. IEEE Trans Autom Sci Eng 19(2):1003–1016. https://doi.org/10.1109/TASE.2021.3053006

    Article  MATH  Google Scholar 

  24. Daniels JI, Ha LK, Ochotta T et al (2007) Robust smooth feature extraction from point clouds. In: Proceedings of the IEEE International Conference on Shape Modeling and Applications 2007. IEEE Computer Society, USA, SMI ’07, pp 123–136. https://doi.org/10.1109/SMI.2007.32

  25. Ohtake Y, Belyaev A, Seidel HP (2004) Ridge-valley lines on meshes via implicit surface fitting. ACM Trans Graph 23(3):609–612. https://doi.org/10.1145/1015706.1015768

    Article  MATH  Google Scholar 

  26. Lin Y, Wang C, Cheng J et al (2015) Line segment extraction for large scale unorganized point clouds. ISPRS J Photogramm Remote Sens 102:172–183. https://doi.org/10.1016/j.isprsjprs.2014.12.027

    Article  MATH  Google Scholar 

  27. Stylianou G, Farin G (2004) Crest lines for surface segmentation and flattening. IEEE Trans Vis Comput Graph 10(5):536–544. https://doi.org/10.1109/TVCG.2004.24

    Article  MATH  Google Scholar 

  28. Hildebrandt K, Polthier K, Wardetzky M (2005) Smooth feature lines on surface meshes. In: Proceedings of the Third Eurographics Symposium on Geometry Processing. Eurographics Association, Goslar, DEU, SGP ’05, pp 85–90

  29. Gao Q, Yamaguchi Y (2019) Extraction of coherent and smooth feature lines from meshes with fine details. Comput Graph 82:222–231. https://doi.org/10.1016/j.cag.2019.05.020

    Article  MATH  Google Scholar 

  30. Wang Q, Sohn H, Cheng JC (2019) Development of high-accuracy edge line estimation algorithms using terrestrial laser scanning. Autom Constr 101:59–71. https://doi.org/10.1016/j.autcon.2019.01.009

    Article  MATH  Google Scholar 

  31. Hackel T, Wegner JD, Schindler K (2016) Contour detection in unstructured 3D point clouds. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, Las Vegas, NV, USA, pp 1610–1618. https://doi.org/10.1109/CVPR.2016.178

  32. Loizou M, Averkiou M, Kalogerakis E (2020) Learning part boundaries from 3D point clouds. Comput Graph Forum 39(5):183–195. https://doi.org/10.1111/cgf.14078

    Article  MATH  Google Scholar 

  33. Matveev A, Rakhimov R, Artemov A et al (2022) Def: deep estimation of sharp geometric features in 3D shapes. ACM Trans Graph. https://doi.org/10.1145/3528223.3530140

    Article  MATH  Google Scholar 

  34. Hu Z, Zhen M, Bai X et al (2020) Jsenet: joint semantic segmentation and edge detection network for 3D point clouds. In: Vedaldi A, Bischof H, Brox T et al (eds) Computer vision—ECCV 2020. Springer International Publishing, Cham, pp 222–239

    Chapter  Google Scholar 

  35. Bazazian D, Parés ME (2021) Edc-net: edge detection capsule network for 3D point clouds. Appl Sci 11(4):1833. https://doi.org/10.3390/app11041833

    Article  MATH  Google Scholar 

  36. Himeur CE, Lejemble T, Pellegrini T et al (2021) Pcednet: a lightweight neural network for fast and interactive edge detection in 3D point clouds. ACM Trans Graph. https://doi.org/10.1145/3481804

    Article  Google Scholar 

  37. Bode L, Weinmann M, Klein R (2023) Bounded: neural boundary and edge detection in 3D point clouds via local neighborhood statistics. ISPRS J Photogramm Remote Sens 205:334–351. https://doi.org/10.1016/j.isprsjprs.2023.09.023

    Article  MATH  Google Scholar 

  38. Feng YF, Shen LY, Yuan CM et al (2023) Deep shape representation with sharp feature preservation. Comput Aided Des 157:103468. https://doi.org/10.1016/j.cad.2022.103468

    Article  MathSciNet  MATH  Google Scholar 

  39. Ye Y, Yi R, Gao Z et al (2023) Nef: neural edge fields for 3D parametric curve reconstruction from multi-view images. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 8486–8495

  40. Vaswani A, Shazeer N, Parmar N et al (2017) Attention is all you need. In: Guyon I, Luxburg UV, Bengio S et al (eds) Advances in neural information processing systems

  41. Lu D, Xie Q, Gao K et al (2022) 3dctn: 3D convolution-transformer network for point cloud classification. IEEE Trans Intell Transp Syst 23(12):24854–24865. https://doi.org/10.1109/TITS.2022.3198836

    Article  Google Scholar 

  42. Zhao H, Jiang L, Jia J et al (2021) Point transformer. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). IEEE, Montreal, QC, Canada, pp 16239–16248. https://doi.org/10.1109/ICCV48922.2021.01595

  43. Du H, Yan X, Wang J et al (2022) Point cloud upsampling via cascaded refinement network. In: Proceedings of the Asian Conference on Computer Vision (ACCV). Springer, Macao, China, pp 586–601. https://doi.org/10.1007/978-3-031-26319-4_7

  44. Yu X, Rao Y, Wang Z et al (2021) Pointr: diverse point cloud completion with geometry-aware transformers. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). IEEE, Montreal, QC, Canada, pp 12478–12487. https://doi.org/10.1109/ICCV48922.2021.01227

  45. Thürrner G, Wüthrich CA (1998) Computing vertex normals from polygonal facets. J Graph Tools 3(1):43–46. https://doi.org/10.1080/10867651.1998.10487487

    Article  MATH  Google Scholar 

  46. Max N (1999) Weights for computing vertex normals from facet normals. J Graph Tools 4(2):1–6. https://doi.org/10.1080/10867651.1999.10487501

    Article  MATH  Google Scholar 

  47. Koch S, Matveev A, Jiang Z et al (2019) Abc: a big cad model dataset for geometric deep learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, Long Beach, CA, USA, pp 9593–9603. https://doi.org/10.1109/CVPR.2019.00983

  48. Besl PJ, McKay ND (1992) Method for registration of 3-D shapes. In: Sensor Fusion IV: Control Paradigms and Data Structures, International Society for Optics and Photonics, pp 586–606. https://doi.org/10.1117/12.57955

  49. Moscoso Thompson E, Arvanitis G, Moustakas K, et al (2019) Shrec’19 track: feature curve extraction on triangle meshes. In: 12th EG Workshop 3D Object Retrieval 2019, Italy, pp 1–8

  50. Johnson A, Hebert M (1998) Surface matching for object recognition in complex three-dimensional scenes. Image Vis Comput 16(9):635–651. https://doi.org/10.1016/S0262-8856(98)00074-2

    Article  MATH  Google Scholar 

  51. Frome A, Huber D, Kolluri R et al (2004) Recognizing objects in range data using regional point descriptors. In: Pajdla T, Matas J (eds) Computer Vision—ECCV 2004. Springer Berlin Heidelberg, Berlin, Heidelberg, pp 224–237. https://doi.org/10.1007/978-3-540-24672-5_18

  52. Tombari F, Salti S, Di Stefano L (2010) Unique signatures of histograms for local surface description. In: Daniilidis K, Maragos P, Paragios N (eds) Computer vision – ECCV 2010. Springer Berlin Heidelberg, Berlin, Heidelberg, pp 356–369. https://doi.org/10.1007/978-3-642-15558-1_26

  53. Rusu RB, Blodow N, Marton ZC et al (2008) Aligning point cloud views using persistent feature histograms. In: 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, pp 3384–3391. https://doi.org/10.1109/IROS.2008.4650967

Download references

Funding

This work was supported by the Shaanxi Science and Technology Association Youth Talent Support Program (Grant number: 20230115) and the National Natural Science Foundation of China (Grant number: 61802311).

Author information

Authors and Affiliations

Authors

Contributions

All authors contributed significantly to this work. Yifei Xie experimented with the proposed method. Zhikun Tu conducted comparisons with PBRG, SGLBP, EC-Net, NerVE, and PIE-Net, as well as the ablation studies. Tong Yang processed the experimental results. Yuhe Zhang proposed the main idea. Xinyu Zhou supervised the experiment procedure. All authors read and approved the final manuscript.

Corresponding authors

Correspondence to Yuhe Zhang or Xinyu Zhou.

Ethics declarations

Conflict of interest

The authors have no conflict of interest to declare that are relevant to the content of this article.

Ethical approval

Not applicable.

Consent

Not applicable.

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

Xie, Y., Tu, Z., Yang, T. et al. EdgeFormer: local patch-based edge detection transformer on point clouds. Pattern Anal Applic 28, 11 (2025). https://doi.org/10.1007/s10044-024-01386-6

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s10044-024-01386-6

Keywords

Navigation