Abstract
The skeletons extracted from 3D point clouds depict the general distributions of the mesh surfaces, which are affected by the local geometrical relations embedded in the neighboring points. However, the local mesh geometry is still not effectively utilized by the popular contraction based skeleton extraction method LOP and its variants. Therefore, this paper improves LOP from two aspects based on the local geometrical distributions. One is the bilateral filter based weighting scheme which additionally takes curvature similarities between neighboring points to better distribute the samples and the other is the eigenvalue based adaptive radius scheme which makes the contraction area varied according to the local shape. These two updates combine together so that an effective contraction of samples during optimization can be obtained. The experiments demonstrate that the improved LOP can obtain more efficient skeleton extractions than existing methods.
Supported by the Natural Science Foundation of Anhui Province (2108085MF210, 1908085MF187).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Au, O.K.C., Tai, C.L., Chu, H.K., Cohen-Or, D., Lee, T.Y.: Skeleton extraction by mesh contraction. ACM Trans. Graph. 27(3), 1–10 (2008)
Bærentzen, A., Rotenberg, E.: Skeletonization via local separators. ACM Trans. Graph. 40(5), 1–18 (2021)
Banterle, F., Corsini, M., Cignoni, P., Scopigno, R.: A low-memory, straightforward and fast bilateral filter through subsampling in spatial domain. Comput. Graph. Forum 31, 19–32 (2012)
Batchuluun, G., Kang, J.K., Nguyen, D.T., Pham, T.D., Arsalan, M., Park, K.R.: Action recognition from thermal videos using joint and skeleton information. IEEE Access 9, 11716–11733 (2021)
Bogo, F., Romero, J., Loper, M., Black, M.J.: FAUST: dataset and evaluation for 3D mesh registration. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3794–3801 (2014)
Bronstein, A.M., Bronstein, M.M., Kimmel, R.: Numerical Geometry of Non-rigid Shapes. Springer, New York (2008). https://doi.org/10.1007/978-0-387-73301-2
Cao, J., Tagliasacchi, A., Olson, M., Zhang, H., Su, Z.: Point cloud skeletons via Laplacian based contraction. In: Shape Modeling International Conference, pp. 187–197. IEEE (2010)
Chen, R., et al.: Multiscale feature line extraction from raw point clouds based on local surface variation and anisotropic contraction. IEEE Trans. Autom. Sci. Eng. 19(2), 1003–2022 (2021)
Cheng, J., et al.: Skeletonization via dual of shape segmentation. Comput. Aided Geomet. Design 80, 101856 (2020)
Chu, Y., Wang, W., Li, L.: Robustly extracting concise 3D curve skeletons by enhancing the capture of prominent features. IEEE Trans. Visual. Comput. Graph, pp. 1–1 (2022)
Cornea, N.D., Silver, D., Min, P.: Curve-skeleton properties, applications, and algorithms. IEEE Trans. Visual Comput. Graph. 13(3), 530 (2007)
Dey, S.: Subpixel dense refinement network for skeletonization. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 258–259 (2020)
Fang, X., Zhou, Q., Shen, J., Jacquemin, C., Shao, L.: Text image deblurring using kernel sparsity prior. IEEE Trans. Cybernet. 50(3), 997–1008 (2018)
Fu, L., Liu, J., Zhou, J., Zhang, M., Lin, Y.: Tree skeletonization for raw point cloud exploiting cylindrical shape prior. IEEE Access 8, 27327–27341 (2020)
Ghanem, M.A., Anani, A.A.: Binary image skeletonization using 2-stage U-Net. arXiv preprint arXiv:2112.11824 (2021)
Huang, H., Li, D., Zhang, H., Ascher, U., Cohen-Or, D.: Consolidation of unorganized point clouds for surface reconstruction. ACM Trans. Graph. 28(5), 1–7 (2009)
Huang, H., Wu, S., Cohen-Or, D., Gong, M., Zhang, H., Li, G., Chen, B.: L1-medial skeleton of point cloud. ACM Trans. Graph. 32(4), 1–8 (2013)
Jalba, A.C., Kustra, J., Telea, A.C.: Surface and curve skeletonization of large 3D models on the GPU. IEEE Trans. Pattern Anal. Mach. Intell. 35(6), 1495–1508 (2012)
Jalba, A.C., Sobiecki, A., Telea, A.C.: An unified multiscale framework for planar, surface, and curve skeletonization. IEEE Trans. Pattern Anal. Mach. Intell. 38(1), 30–45 (2015)
Jiang, A., Liu, J., Zhou, J., Zhang, M.: Skeleton extraction from point clouds of trees with complex branches via graph contraction. Vis. Comput. 37(8), 2235–2251 (2020). https://doi.org/10.1007/s00371-020-01983-6
Ko, D.H., Hassan, A.U., Suk, J., Choi, J.: SKFont: Skeleton-driven Korean font generator with conditional deep adversarial networks. Int. J. Doc. Anal. Recogn. 24(4), 325–337 (2021)
Li, L., Wang, W.: Contracting medial surfaces isotropically for fast extraction of centred curve skeletons. In: Computer Graphics Forum, vol. 36, pp. 529–539 (2017)
Li, L., Wang, W.: Improved use of LOP for curve skeleton extraction. In: Computer Graphics Forum, vol. 37, pp. 313–323 (2018)
Lin, C., Li, C., Liu, Y., Chen, N., Choi, Y.K., Wang, W.: Point2Skeleton: learning skeletal representations from point clouds. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4277–4286 (2021)
Lipman, Y., Cohen-Or, D., Levin, D., Tal-Ezer, H.: Parameterization-free projection for geometry reconstruction. ACM Trans. Graph. 26(3), 22-es (2007)
Liu, Y., Guo, J., Benes, B., Deussen, O., Zhang, X., Huang, H.: TreePartNet: neural decomposition of point clouds for 3D tree reconstruction. ACM Trans. Graph. 40(6) (2021)
Livesu, M., Guggeri, F., Scateni, R.: Reconstructing the curve-skeletons of 3D shapes using the visual hull. IEEE Trans. Visual Comput. Graph. 18(11), 1891–1901 (2012)
Lu, L., Lévy, B., Wang, W.: Centroidal Voronoi tessellation of line segments and graphs. Comput. Graph. Forum 31, 775–784 (2012)
Luo, S., et al.: Laser curve extraction of wheelset based on deep learning skeleton extraction network. Sensors 22(3), 859 (2022)
Nathan, S., Kansal, P.: SkeletonNetV2: a dense channel attention blocks for skeleton extraction. In: IEEE/CVF International Conference on Computer Vision, pp. 2142–2149 (2021)
Panichev, O., Voloshyna, A.: U-Net based convolutional neural network for skeleton extraction. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 1186–1189 (2019)
Preiner, R., Mattausch, O., Arikan, M., Pajarola, R., Wimmer, M.: Continuous projection for fast L1 reconstruction. ACM Trans. Graph. 33(4), 1–13 (2014)
Qin, H., Han, J., Li, N., Huang, H., Chen, B.: Mass-driven topology-aware curve skeleton extraction from incomplete point clouds. IEEE Trans. Visual Comput. Graph. 26(9), 2805–2817 (2019)
Ritter, M., Schiffner, D., Harders, M.: Robust reconstruction of curved line structures in noisy point clouds. Visual Inform. 5(3), 1–14 (2021)
Song, C., Pang, Z., Jing, X., Xiao, C.: Distance field guided \(l_1\)-median skeleton extraction. Vis. Comput. 34(2), 243–255 (2018)
Tagliasacchi, A., Alhashim, I., Olson, M., Zhang, H.: Mean curvature skeletons. Comput. Graphics Forum 31, 1735–1744 (2012)
Tagliasacchi, A., Delame, T., Spagnuolo, M., Amenta, N., Telea, A.: 3D skeletons: a state-of-the-art report. Compu. Graph. Forum 35, 573–597 (2016)
Tomasi, C., Manduchi, R.: Bilateral filtering for gray and color images. In: International Conference on Computer Vision, pp. 839–846 (1998)
Wang, Y.S., Lee, T.Y.: Curve-skeleton extraction using iterative least squares optimization. IEEE Trans. Visual Comput. Graphics 14(4), 926–936 (2008)
Yan, Y., Letscher, D., Ju, T.: Voxel cores: efficient, robust, and provably good approximation of 3D medial axes. ACM Trans. Graphics 37(4), 1–13 (2018)
Yan, Y., Sykes, K., Chambers, E., Letscher, D., Ju, T.: Erosion thickness on medial axes of 3D shapes. ACM Trans. Graph. 35(4), 1–12 (2016)
Yang, L., Oyen, D., Wohlberg, B.: A novel algorithm for skeleton extraction from images using topological graph analysis. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 1162–1166 (2019)
Zhang, L., Hu, F., Chu, Z., Bentley, E., Kumar, S.: 3D transformative routing for UAV swarming networks: a skeleton-guided, GPS-free approach. IEEE Trans. Veh. Technol. 70(4), 3685–3701 (2021)
Zhou, J., Liu, J., Zhang, M.: Curve skeleton extraction via k-nearest-neighbors based contraction. Int. J. Appl. Math. Comput. Sci. 30(1), 123–132 (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Fang, X., Hu, L., Ye, F., Wang, L. (2022). Locally Geometry-Aware Improvements of LOP for Efficient Skeleton Extraction. In: Yu, S., et al. Pattern Recognition and Computer Vision. PRCV 2022. Lecture Notes in Computer Science, vol 13536. Springer, Cham. https://doi.org/10.1007/978-3-031-18913-5_1
Download citation
DOI: https://doi.org/10.1007/978-3-031-18913-5_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-18912-8
Online ISBN: 978-3-031-18913-5
eBook Packages: Computer ScienceComputer Science (R0)