Abstract
3D shape segmentation serves as the base of semantic shape analysis and becomes a hot research topic in recent years. Many segmentation methods are devised by feeding surface based geometric descriptors into a deep neural network. Most of the existing approaches assume that the surface variation information is rich enough to characterize a 3D shape, and thus perform all the constituent steps on the triangle mesh representation. However, triangle based learning networks suffer from how to define the convolutional operator, unlike the trivial situation of regular pixels or voxels. Observing that the volumetric representation is the dual of the surface representation, we design a volumetric encoder-decoder architecture, named V-SegNet, which works by lifting surface based geometric features to the enclosed voxels and then training a deep volumetric network. In the inference stage, we build the voxelization of a given 3D object, then predict the label for each voxel lying in the interior of the given shape, and finally generate the labeling information for each triangle face. The experimental results show that V-SegNet, working in a surface-volume-surface fashion, further improves the segmentation performance.
Y. Liu and W. Long—Contribute equally to this work.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Milano, F., Loquercio, A., Rosinol, A., Scaramuzza, D., Carlone, L.: Primal-dual mesh convolutional neural networks. In: Conference on Neural Information Processing Systems, pp. 952–963 (2020)
Shapira, L., Shamir, A., Cohen-Or, D.: Consistent mesh partitioning and skeletonisation using the shape diameter function. Vis. Comput. 24(4), 249–259 (2008)
Lim, J.J., Khosla, A., Torralba, A.: FPM: fine pose parts-based model with 3D CAD models. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8694, pp. 478–493. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10599-4_31
Huang, H., Kalogerakis, E., Yumer, E., Mech, R.: Shape synthesis from sketches via procedural models and convolutional networks. IEEE Trans. Vis. Comput. Graph. 23(8), 2003–2013 (2016)
Kalogerakis, E., Hertzmann, A., Singh, K.: Learning 3D mesh segmentation and labeling. ACM Trans. Graph. 29, 1–12 (2010)
Guo, K., Zou, D., Chen, X.: 3D mesh labeling via deep convolutional neural networks. ACM Trans. Graph. 35(1), 1–12 (2015)
Wang, Z., Lu, F.: VoxSegNet: volumetric CNNs for semantic part segmentation of 3D shapes. IEEE Trans. Vis. Comput. Graph. 26(9), 2919–2930 (2019)
Shu, Z., Qi, C., Xin, S., Hu, C., Wang, L., Zhang, Y., Liu, L.: Unsupervised 3D shape segmentation and co-segmentation via deep learning. Comput. Aid. Geom. Des. 43, 39–52 (2016)
Gal, R., Cohen-Or, D.: Salient geometric features for partial shape matching and similarity. ACM Trans. Graph. 25(1), 130–150 (2006)
Shapira, L., Shalom, S., Shamir, A., Cohen-Or, D., Zhang, H.: Contextual part analogies in 3D objects. Int. J. Comput. Vis. 89(2–3), 309–326 (2010)
Kalogerakis, E., Averkiou, M., Maji, S., Chaudhuri, S.: 3D shape segmentation with projective convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3779–3788 (2017)
Maturana, D., Scherer, S.: VoxNet: a 3D convolutional neural network for real-time object recognition. In: IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 922–928. IEEE (2015)
Qi, C.R., Su, H., Nießner, M., Dai, A., Yan, M., Guibas, L.J.: 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 (2016)
Riegler, G., Osman Ulusoy, A., Geiger, A.: OctNet: learning deep 3D representations at high resolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3577–3586 (2017)
Wang, P.S., Liu, Y., Guo, Y.X., Sun, C.Y., Tong, X.: O-CNN: octree-based convolutional neural networks for 3D shape analysis. ACM Trans. Graph. 36(4), 1–11 (2017)
Yu, F., Liu, K., Zhang, Y., Zhu, C., Xu, K.: PartNet: a recursive part decomposition network for fine-grained and hierarchical shape segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9491–9500 (2019)
Hu, S.M., Liu, Z.N., Guo, M.H., Cai, J.X., Huang, J., Mu, T.J., Martin, R.R.: Subdivision-based mesh convolution networks. ACM Trans. Graph. 41(3), 1–16 (2022)
Hanocka, R., Hertz, A., Fish, N., Giryes, R., Fleishman, S., Cohen-Or, D.: MeshCNN: a network with an edge. ACM Trans. Graph. 38(4), 1–12 (2019)
Lahav, A., Tal, A.: MeshWalker: deep mesh understanding by random walks. ACM Trans. Graph. 39(6), 1–13 (2020)
Boykov, Y., Veksler, O., Zabih, R.: Fast approximate energy minimization via graph cuts. IEEE Trans. Pattern Anal. Mach. Intell. 23(11), 1222–1239 (2001)
Moon, G., Chang, J.Y., Lee, K.M.: V2V-PoseNet: voxel-to-voxel prediction network for accurate 3D hand and human pose estimation from a single depth map. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5079–5088 (2018)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28
Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431–3440 (2015)
Wang, Y., Gong, M., Wang, T., Cohen-Or, D., Zhang, H., Chen, B.: Projective analysis for 3D shape segmentation. ACM Trans. Graph. 32(6), 1–12 (2013)
Chen, X., Golovinskiy, A., Funkhouser, T.: A benchmark for 3D mesh segmentation. ACM Trans. Graph. 28(3), 1–12 (2009)
Wang, Y., Asafi, S., Van Kaick, O., Zhang, H., Cohen-Or, D., Chen, B.: Active co-analysis of a set of shapes. ACM Trans. Graph. 31(6), 1–10 (2012)
Hu, R., Fan, L., Liu, L.: Co-segmentation of 3D shapes via subspace clustering. Comput. Graph. Forum 31(5), 1703–1713 (2012)
Acknowledgments
This work is supported by the National Natural Science Foundation of China (61872321, 62172356, 61972350), Natural Science Foundation of Zhejiang Province (LY22F020026), and Ningbo Major Special Projects of the “Science and Technology Innovation 2025” (2020Z005, 2020Z007, 2021Z012).
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
Liu, Y., Long, W., Shu, Z., Yi, S., Xin, S. (2022). Voxel-Based 3D Shape Segmentation Using Deep Volumetric Convolutional Neural Networks. In: Magnenat-Thalmann, N., et al. Advances in Computer Graphics. CGI 2022. Lecture Notes in Computer Science, vol 13443. Springer, Cham. https://doi.org/10.1007/978-3-031-23473-6_38
Download citation
DOI: https://doi.org/10.1007/978-3-031-23473-6_38
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-23472-9
Online ISBN: 978-3-031-23473-6
eBook Packages: Computer ScienceComputer Science (R0)