Abstract
Sampling and interpolation are pivotal in the design of 3D neural networks. Presently, farthest point sampling and \(k\)-NN interpolation are the predominant techniques. Nonetheless, the former can lead to information loss in feature-rich regions, while the latter might introduce noticeable discontinuities, compromising neural network performance. In this research, we address information loss with a novel method, DistrFPS, that considers the input information distribution during the farthest point sampling. Leveraging DistrFPS, we introduce a guided sampling module to retain crucial information for subsequent network layers. We also propose a continuous interpolation module grounded in barycentric interpolation to ensure spatial coherent feature propagation to higher resolution network layers. Our approach’s efficacy in preserving information is demonstrated empirically through signal reconstruction in both 2D and 3D realms. Comprehensive experiments on S3DIS, ScanNet, and ShapeNetPart affirm the advantages of our technique for point-based networks.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Supplementary material at: https://doi.org/10.5281/zenodo.10494633.
- 2.
References
Armeni, I., et al.: 3D semantic parsing of large-scale indoor spaces. In: CVPR (2016)
Cao, T.T., Nanjappa, A., Gao, M., Tan, T.S.: A GPU accelerated algorithm for 3D Delaunay triangulation. In: I3D (2014)
Chen, X., Ma, H., Wan, J., Li, B., Xia, T.: Multi-view 3D object detection network for autonomous driving. In: CVPR (2017)
Chiang, H.Y., Lin, Y.L., Liu, Y.C., Hsu, W.H.: A unified point-based framework for 3D segmentation. In: 3DV (2019)
Choy, C., Gwak, J., Savarese, S.: 4D spatio-temporal convnets: Minkowski convolutional neural networks. In: CVPR (2019)
Dai, A., Chang, A.X., Savva, M., Halber, M., Funkhouser, T., Nießner, M.: Scannet: richly-annotated 3D reconstructions of indoor scenes. In: CVPR (2017)
Dovrat, O., Lang, I., Avidan, S.: Learning to sample. In: CVPR (2019)
Eldar, Y., Lindenbaum, M., Porat, M., Zeevi, Y.Y.: The farthest point strategy for progressive image sampling. TIP 6(9), 1305–1315 (1997)
Fan, S., Dong, Q., Zhu, F., Lv, Y., Ye, P., Wang, F.Y.: SCF-net: learning spatial contextual features for large-scale point cloud segmentation. In: CVPR (2021)
Gouraud, H.: Continuous shading of curved surfaces. TC (1971)
Graham, B., Engelcke, M., Van Der Maaten, L.: 3D semantic segmentation with submanifold sparse convolutional networks. In: CVPR (2018)
Guibas, L., Stolfi, J.: Primitives for the manipulation of general subdivisions and the computation of Voronoi. TOG 4(2), 74–123 (1985)
Guo, M.H., Cai, J.X., Liu, Z.N., Mu, T.J., Martin, R.R., Hu, S.M.: PCT: point cloud transformer. CVM 7, 187–199 (2021)
Hu, Q., et al.: RandLA-net: efficient semantic segmentation of large-scale point clouds. In: CVPR (2020)
Huang, Q., Wang, W., Neumann, U.: Recurrent slice networks for 3D segmentation of point clouds. In: CVPR (2018)
Kanezaki, A., Matsushita, Y., Nishida, Y.: Rotationnet: joint object categorization and pose estimation using multiviews from unsupervised viewpoints. In: CVPR (2018)
Lai, X., et al.: Stratified transformer for 3D point cloud segmentation. In: CVPR (2022)
Landrieu, L., Simonovsky, M.: Large-scale point cloud semantic segmentation with superpoint graphs. In: CVPR (2018)
Lang, A.H., Vora, S., Caesar, H., Zhou, L., Yang, J., Beijbom, O.: Pointpillars: fast encoders for object detection from point clouds. In: CVPR (2019)
Lang, I., Manor, A., Avidan, S.: Samplenet: differentiable point cloud sampling. In: CVPR (2020)
Li, B.: 3D fully convolutional network for vehicle detection in point cloud. In: IROS (2017)
Li, Y., Bu, R., Sun, M., Wu, W., Di, X., Chen, B.: PointCNN: convolution on x-transformed points. In: NeurIPS (2018)
Lin, Y., Chen, L., Huang, H., Ma, C., Han, X., Cui, S.: Task-aware sampling layer for point-wise analysis. TVCG (2022)
Liu, Y., Fan, B., Xiang, S., Pan, C.: Relation-shape convolutional neural network for point cloud analysis. In: CVPR (2019)
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: ICLR (2022)
Maturana, D., Scherer, S.: VoxNet: a 3D convolutional neural network for real-time object recognition. In: IROS (2015)
Nekrasov, A., Schult, J., Litany, O., Leibe, B., Engelmann, F.: Mix3D: Out-of-Context Data Augmentation for 3D Scenes (2021)
Paszke, A., et al.: PyTorch: an imperative style, high-performance deep learning library. In: NeurIPS (2019)
Qi, C.R., Su, H., Mo, K., Guibas, L.J.: PointNet: deep learning on point sets for 3D classification and segmentation. In: CVPR (2017)
Qi, C.R., Yi, L., Su, H., Guibas, L.J.: PointNet++: deep hierarchical feature learning on point sets in a metric space. In: NeurIPS (2017)
Qian, G., Hammoud, H., Li, G., Thabet, A., Ghanem, B.: ASSANet: an anisotropic separable set abstraction for efficient point cloud representation learning. In: NeurIPS (2021)
Qian, G., et al.: PointNeXt: revisiting PointNet++ with improved training and scaling strategies. In: NeurIPS (2022)
Ran, H., Liu, J., Wang, C.: Surface representation for point clouds. In: CVPR (2022)
Ran, H., Zhuo, W., Liu, J., Lu, L.: Learning inner-group relations on point clouds. In: ICCV (2021)
Riegler, G., Osman Ulusoy, A., Geiger, A.: Octnet: learning deep 3D representations at high resolutions. In: ICCV (2017)
Robert, D., Vallet, B., Landrieu, L.: Learning multi-view aggregation in the wild for large-scale 3D semantic segmentation. In: CVPR (2022)
Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: MICCAI (2015)
Rosu, R.A., Schütt, P., Quenzel, J., Behnke, S.: LatticeNet: fast spatio-temporal point cloud segmentation using permutohedral lattices. Auton. Robots 46(1), 45–60 (2022)
Song, S., Yu, F., Zeng, A., Chang, A.X., Savva, M., Funkhouser, T.: Semantic scene completion from a single depth image. In: CVPR (2017)
Su, H., et al.: Splatnet: sparse lattice networks for point cloud processing. In: CVPR (2018)
Su, H., Maji, S., Kalogerakis, E., Learned-Miller, E.: Multi-view convolutional neural networks for 3D shape recognition. In: ICCV (2015)
Tang, L., Zhan, Y., Chen, Z., Yu, B., Tao, D.: Contrastive boundary learning for point cloud segmentation. In: CVPR (2022)
Thomas, H., Qi, C.R., Deschaud, J.E., Marcotegui, B., Goulette, F., Guibas, L.: KPConv: flexible and deformable convolution for point clouds. In: ICCV (2019)
Virtanen, P., et al.: SciPy 1.0: fundamental algorithms for scientific computing in Python. Nature Methods 17(3), 261–272 (2020)
Wang, P.S., Liu, Y., Guo, Y.X., Sun, C.Y., Tong, X.: O-CNN: octree-based convolutional neural networks for 3D shape analysis. TOG 36(4), 1–11 (2017)
Wang, Y., Ji, R., Chang, S.F.: Label propagation from ImageNet to 3D point clouds. In: CVPR (2013)
Wang, Y., Sun, Y., Liu, Z., Sarma, S.E., Bronstein, M.M., Solomon, J.M.: Dynamic graph CNN for learning on point clouds. TOG 38(5), 1–12 (2019)
Wang, Z., Bovik, A., Sheikh, H., Simoncelli, E.: Image quality assessment: from error visibility to structural similarity. TIP 13(4), 600–612 (2004)
Wu, X., Lao, Y., Jiang, L., Liu, X., Zhao, H.: Point transformer V2: grouped vector attention and partition-based pooling. In: NeurIPS (2022)
Wu, Z., et al.: 3D shapenets: a deep representation for volumetric shapes. In: CVPR (2015)
Xiang, T., Zhang, C., Song, Y., Yu, J., Cai, W.: Walk in the cloud: learning curves for point clouds shape analysis. In: ICCV (2021)
Xu, M., Ding, R., Zhao, H., Qi, X.: PAConv: position adaptive convolution with dynamic kernel assembling on point clouds. In: CVPR (2021)
Xu, Y., Fan, T., Xu, M., Zeng, L., Qiao, Y.: Spidercnn: deep learning on point sets with parameterized convolutional filters. In: ECCV (2018)
Yan, X., Zheng, C., Li, Z., Wang, S., Cui, S.: PointASNL: robust point clouds processing using nonlocal neural networks with adaptive sampling. In: CVPR (2020)
Yang, J., et al.: Modeling point clouds with self-attention and gumbel subset sampling. In: CVPR (2019)
Yi, L., et al.: A scalable active framework for region annotation in 3D shape collections. TOG 35(6), 1–12 (2016)
Zhang, C., Wan, H., Shen, X., Wu, Z.: PatchFormer: an efficient point transformer with patch attention. In: CVPR (2022)
Zhang, Z., Hua, B.S., Yeung, S.K.: Shellnet: efficient point cloud convolutional neural networks using concentric shells statistics. In: ICCV (2019)
Zhao, H., Jiang, L., Fu, C.W., Jia, J.: Pointweb: enhancing local neighborhood features for point cloud processing. In: CVPR (2019)
Zhao, H., Jiang, L., Jia, J., Torr, P.H., Koltun, V.: Point transformer. In: ICCV (2021)
Acknowledgements
The authors would like to thank the CVM 2024 reviewers and program chairs for their valuable feedback. This work is supported by National Natural Science Foundation of China (No. 62032011).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Zhang, G., Liu, X. (2024). Point Cloud Segmentation with Guided Sampling and Continuous Interpolation. In: Zhang, FL., Sharf, A. (eds) Computational Visual Media. CVM 2024. Lecture Notes in Computer Science, vol 14592. Springer, Singapore. https://doi.org/10.1007/978-981-97-2095-8_6
Download citation
DOI: https://doi.org/10.1007/978-981-97-2095-8_6
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-97-2094-1
Online ISBN: 978-981-97-2095-8
eBook Packages: Computer ScienceComputer Science (R0)