AI Chat Paper
Note: Please note that the following content is generated by AMiner AI. SciOpen does not take any responsibility related to this content.
{{lang === 'zh_CN' ? '文章概述' : 'Summary'}}
{{lang === 'en_US' ? '中' : 'Eng'}}
Chat more with AI
Powered by AMiner. Clicking this button will take you away from SciOpen.
Home Journal of Computer Science and Technology Article
Article Link
Cite
EndNote(RIS) BibTeX
Collect
Submit Manuscript
Show Outline
Outline
Show full outline
Hide outline
Outline
Show full outline
Hide outline
Regular Paper

Point-Voxel Based Geometry-Adaptive Network for 3D Point Cloud Analysis

Beijing Engineering Research Center of Industrial Spectrum Imaging, School of Automation and Electrial Engineering University of Science and Technology Beijing, Beijing 100083, China
Shunde Innovation School, University of Science and Technology Beijing, Foshan 528399, China
Beijing Institute of Electronic System Engineering, Beijing 100854, China
School of Intelligence Science and Technology, University of Science and Technology Beijing, Beijing 100083, China
Institute of Artificial Intelligence, University of Science and Technology Beijing, Beijing 100083, China
Show Author Information

Abstract

Point cloud analysis is challenging because of the unordered and irregular data structure of point clouds. To describe geometric information in point clouds, existing methods mainly use convolution, graph, and attention operations to construct sophisticated local aggregation operators. These operators work well in extracting local information but bring unfavorable inference latency due to high computation complexity. To solve the above problem, this paper presents a novel point-voxel based geometry-adaptive network (PVGANet), which combines multiple representations of point and voxel to describe the point cloud from different granularities and can obtain features of different scales effectively. To extract fine-grained geometric features, we design the position-adaptive pooling operator, which uses point pairs’ relative position and feature similarity to weight and aggregate the point features at local areas of point clouds. To extract coarse-grained local features, we design a depth-wise convolution operator, which conducts the depth-wise convolution on voxel grids. With an easy addition, fine-grained geometric and coarse-grained local features can be fused, and we can use the geometry-adaptive fused features to complete the efficient shape analysis of point clouds, such as shape classification and part segmentation. Extensive experiments on ModelNet40, ScanObjectNN, and ShapeNet Part benchmarks demonstrate that our PVGANet achieves competitive performance compared with the related methods.

Keywords

point cloudgeometric featuremulti-representationpart segmentationshape classification

Electronic Supplementary Material

Download File(s)
JCST-2306-13521-Highlights.pdf (152.8 KB)

References

[1]

Wang S, Jiang Y, Hu J, Fan X, Luo Z, Liu Y, Liu L. Efficient representation and optimization of TPMS-based porous structures for 3D heat dissipation. Computer-Aided Design, 2022, 142: 103123. DOI: 10.1016/j.cad.2021.103123.
Crossref Google Scholar
[2]
Qi C R, Su H, Mo K C, Guibas L J. PointNet: Deep learning on point sets for 3D classification and segmentation. In Proc. the 2017 IEEE Conference on Computer Vision and Pattern Recognition, Jul. 2017, pp.77–85. DOI: 10.1109/CVPR.2017.16.
Crossref
[3]
Su H, Maji S, Kalogerakis E, Learned-Miller E. Multi-view convolutional neural networks for 3D shape recognition. In Proc. the 2015 IEEE International Conference on Computer Vision, Dec. 2015, pp.945–953. DOI: 10.1109/ICCV.2015.114.
Crossref
[4]
Wu Z, Song S, Khosla A, Yu F, Zhang L, Tang X, Xiao J. 3D ShapeNets: A deep representation for volumetric shapes. In Proc. the 2015 IEEE Conference on Computer Vision and Pattern Recognition, Jun. 2015, pp.1912–1920. DOI: 10.1109/CVPR.2015.7298801.
Crossref
[5]
Maturana D, Scherer S. VoxNet: A 3D convolutional neural network for real-time object recognition. In Proc. the 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems, Sept. 28–Oct. 2, 2015, pp.922–928. DOI: 10.1109/IROS.2015.7353481.
Crossref
[6]
Çiçek Ö, Abdulkadir A, Lienkamp S S, Brox T, Ronneberger O. 3D U-Net: Learning dense volumetric segmentation from sparse annotation. In Proc. the 19th International Conference on Medical Image Computing and Computer-Assisted Intervention, Oct. 2016, pp.424–432. DOI: 10.1007/978-3-319-46723-8_49.
Crossref
[7]
Goyal A, Law H, Liu B, Newell A, Deng J. Revisiting point cloud shape classification with a simple and effective baseline. In Proc. the 38th International Conference on Machine Learning, Jul. 2021, pp.3809–3820.
[8]
Hamdi A, Giancola S, Ghanem B. MVTN: Multi-view transformation network for 3D shape recognition. In Proc. the 2021 IEEE/CVF International Conference on Computer Vision, Oct. 2021, pp.1–11. DOI: 10.1109/ICCV48922.2021.00007.
Crossref
[9]
Choy C, Gwak J, Savarese S. 4D spatio-temporal convnets: Minkowski convolutional neural networks. In Proc. the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Jun. 2019, pp.3070–3079. DOI: 10.1109/CVPR.2019.00319.
Crossref
[10]
Tang H, Liu Z, Zhao S, Lin Y, Lin J, Wang H, Han S. Searching efficient 3D architectures with sparse point-voxel convolution. In Proc. the 16th European Conference on Computer Vision, Aug. 2020, pp.685–702. DOI: 10.1007/978-3-030-58604-1_41.
Crossref
[11]
Qi C R, Yi L, Su H, Guibas L J. PointNet++: Deep hierarchical feature learning on point sets in a metric space. In Proc. the 31st International Conference on Neural Information Processing Systems, Dec. 2017, pp.5105–5114.
[12]
Liu Y, Fan B, Xiang S, Pan C. Relation-shape convolutional neural network for point cloud analysis. In Proc. the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Jun. 2019, pp.8887–8896. DOI: 10.1109/CVPR.2019.00910.
Crossref
[13]
Qian G, Hammoud H A A K, Li G, Thabet A, Ghanem B. ASSANet: An anisotropic separable set abstraction for efficient point cloud representation learning. In Proc. the 35th International Conference on Neural Information Processing Systems, Jun. 2021, Article No. 2154, pp.28119 –28130.
[14]
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 Proc. the 10th International Conference on Learning Representations, Apr. 2022.
[15]
Qian G, Li Y, Peng H, Mai J, Hammoud H A A K, Elhoseiny M, Ghanem B. PointNeXt: Revisiting PointNet++ with improved training and scaling strategies. In Proc. the 36th Conference on Neural Information Processing Systems, Nov. 28–Dec. 9, 2022.
[16]
Xu Y, Fan T, Xu M, Zeng L, Qiao Y. SpiderCNN: Deep learning on point sets with parameterized convolutional filters. In Proc. the 15th European Conference on Computer Vision, Sept. 2018, pp.90–105. DOI: 10.1007/978-3-030-01237-3_6.
Crossref
[17]
Li Y, Bu R, Sun M, Wu W, Di X, Chen B. PointCNN: Convolution on X-transformed points. In Proc. the 32nd Conference on Neural Information Processing Systems, Dec. 2018, pp.820–830.
[18]
Qiu S, Anwar S, Barnes N. Dense-resolution network for point cloud classification and segmentation. In Proc. the 2021 IEEE Winter Conference on Applications of Computer Vision, Jan. 2021, pp.3812–3821. DOI: 10.1109/WACV48630.2021.00386.
Crossref
[19]

Cheng S, Chen X, He X, Liu Z, Bai X. PRA-Net: Point relation-aware network for 3D point cloud analysis. IEEE Trans. Image Processing, 2021, 30: 4436–4448. DOI: 10.1109/TIP.2021.3072214.
Crossref Google Scholar
[20]

Wang Y, Sun Y, Liu Z, Sarma S E, Bronstein M M, Solomon J M. Dynamic graph CNN for learning on point clouds. ACM Trans. Graphics, 2019, 38(5): Article No. 146. DOI: 10.1145/3326362.
Crossref Google Scholar
[21]
Li G, Müller M, Thabet A, Ghanem B. DeepGCNs: Can GCNs go as deep as CNNs? In Proc. the 2019 IEEE/CVF International Conference on Computer Vision, Oct. 27–Nov. 2, 2019, pp.9266–9275. DOI: 10.1109/ICCV.2019.00936.
Crossref
[22]
Liu X, Han Z, Liu Y S, Zwicker M. Point2Sequence: Learning the shape representation of 3D point clouds with an attention-based sequence to sequence network. In Proc. the 33rd AAAI Conference on Artificial Intelligence, Jun. 2019, pp.8778–8785. DOI: 10.1609/aaai.v33i01.33018778.
Crossref
[23]
Yan X, Zheng C, Li Z, Wang S, Cui S. PointASNL: Robust point clouds processing using nonlocal neural networks with adaptive sampling. In Proc. the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Jun. 2020, pp.5588–5597. DOI: 10.1109/CVPR42600.2020.00563.
Crossref
[24]

Guo M H, Cai J X, Liu Z N, Mu T J, Martin R R, Hu S M. PCT: Point cloud transformer. Computational Visual Media, 2021, 7(2): 187–199. DOI: 10.1007/s41095-021-0229-5.
Crossref Google Scholar
[25]
Hu Q, Yang B, Xie L, Rosa S, Guo Y, Wang Z, Trigoni N, Markham A. RandLA-Net: Efficient semantic segmentation of large-scale point clouds. In Proc. the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Jun. 2020, pp.11105–11114. DOI: 10.1109/CVPR42600.2020.01112.
Crossref
[26]
Qiu S, Anwar S, Barnes N. Semantic segmentation for real point cloud scenes via bilateral augmentation and adaptive fusion. In Proc. the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Jun. 2021, pp.1757–1767. DOI: 10.1109/CVPR46437.2021.00180.
Crossref
[27]
Nie D, Lan R, Wang L, Ren X. Pyramid architecture for multi-scale processing in point cloud segmentation. In Proc. the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Jun. 2022, pp.17263–17273. DOI: 10.1109/CVPR52688.2022.01677.
Crossref
[28]
Zhao H, Jiang L, Jia J, Torr P H S, Koltun V. Point transformer. In Proc. the IEEE/CVF International Conference on Computer Vision, Oct. 2021, pp.16259–16268.
Crossref
[29]

Qiu S, Anwar S, Barnes N. Geometric back-projection network for point cloud classification. IEEE Trans. Multimedia, 2021, 24: 1943–1955. DOI: 10.1109/TMM.2021.3074240.
Crossref Google Scholar
[30]
Lai X, Liu J, Jiang L, Wang L, Zhao H, Liu S, Qi X, Jia J. Stratified transformer for 3D point cloud segmentation. In Proc. the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Jun. 2022, pp.8490–8499. DOI: 10.1109/CVPR52688.2022.00831.
Crossref
[31]

Song Y, He F, Duan Y, Liang Y, Yan X. A kernel correlation-based approach to adaptively acquire local features for learning 3D point clouds. Computer-Aided Design, 2022, 146: 103196. DOI: 10.1016/j.cad.2022.103196.
Crossref Google Scholar
[32]

Wang S, Liu Y, Wang L, Sun Y, Yin B. PASIFTNet: Scale-and-directional-aware semantic segmentation of point clouds. Computer-Aided Design, 2023, 156: 103462. DOI: 10.1016/j.cad.2022.103462.
Crossref Google Scholar
[33]
You H, Feng Y, Ji R, Gao Y. PVNet: A joint convolutional network of point cloud and multi-view for 3D shape recognition. In Proc. the 26th ACM International Conference on Multimedia, Oct. 2018, pp.1310–1318. DOI: 10.1145/3240508.3240702.
Crossref
[34]
You H, Feng Y, Zhao X, Zou C, Ji R, Gao Y. PVRNet: Point-view relation neural network for 3D shape recognition. In Proc. the 33rd AAAI Conference on Artificial Intelligence, Jul. 2019, pp.9119–9126. DOI: 10.1609/aaai.v33i01.33019119.
Crossref
[35]
Le T, Duan Y. PointGrid: A deep network for 3D shape understanding. In Proc. the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Jun. 2018, pp.9204–9214. DOI: 10.1109/CVPR.2018.00959.
Crossref
[36]
Liu Z, Tang H, Lin Y, Han S. Point-voxel CNN for efficient 3D deep learning. In Proc. the 33rd International Conference on Neural Information Processing Systems, Dec. 2019, p.87.
[37]
Shi S, Guo C, Jiang L, Wang Z, Shi J, Wang X, Li H. PV-RCNN: Point-voxel feature set abstraction for 3D object detection. In Proc. the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Jun. 2020, pp.10526–10535. DOI: 10.1109/CVPR42600.2020.01054.
Crossref
[38]
Noh J, Lee S, Ham B. HVPR: Hybrid voxel-point representation for single-stage 3D object detection. In Proc. the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Jun. 2021, pp.14600–14609. DOI: 10.1109/CVPR46437.2021.01437.
Crossref
[39]
Xu J, Zhang R, Dou J, Zhu Y, Sun J, Pu S. RPVNet: A deep and efficient range-point-voxel fusion network for LiDAR point cloud segmentation. In Proc. the 2021 IEEE/CVF International Conference on Computer Vision, Oct. 2021, pp.16004–16013. DOI: 10.1109/ICCV48922.2021.01572.
Crossref
[40]
Howard A G, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, Andreetto M, Adam H. MobileNets: Efficient convolutional neural networks for mobile vision applications. arXiv: 1704.04861, 2017. https://arxiv.org/abs/1704.04861, Sept. 2024.
[41]
Liu Z, Hu H, Cao Y, Zhang Z, Tong X. A closer look at local aggregation operators in point cloud analysis. In Proc. the 16th European Conference on Computer Vision, Aug. 2020, pp.326–342. DOI: 10.1007/978-3-030-58592-1_20.
Crossref
[42]
Uy M A, Pham Q H, Hua B S, Nguyen T, Yeung S K. Revisiting point cloud classification: A new benchmark dataset and classification model on real-world data. In Proc. the 2019 IEEE/CVF International Conference on Computer Vision, Oct. 27–Nov. 2, 2019, pp.1588–1597. DOI: 10.1109/ICCV.2019.00167.
Crossref
[43]

Yi L, Kim V G, Ceylan D, Shen I C, Yan M, Su H, Lu C, Huang Q, Sheffer A, Guibas L. A scalable active framework for region annotation in 3D shape collections. ACM Trans. Graphics, 2016, 35(6): Article No. 210. DOI: 10.1145/2980179.2980238.
Crossref Google Scholar
Journal of Computer Science and Technology
Volume 39 Issue 5,
September 2024
Pages 1167-1179
DOI: 10.1007/s11390-024-3521-x

{{item.num}}

Comments on this article

Go to comment

< Back to all reports

Review Status: {{reviewData.commendedNum}} Commended , {{reviewData.revisionRequiredNum}} Revision Required , {{reviewData.notCommendedNum}} Not Commended Under Peer Review

Review Comment

Cite this Report
Close
Close
Cite this article:
Zhao T-M, Zeng H, Zhang B-Q, et al. Point-Voxel Based Geometry-Adaptive Network for 3D Point Cloud Analysis. Journal of Computer Science and Technology, 2024, 39(5): 1167-1179. https://doi.org/10.1007/s11390-024-3521-x

215

Views

0

Crossref

0

Web of Science

0

Scopus

0

CSCD

Altmetrics
Received: 18 June 2023
Accepted: 21 April 2024
Published: 05 December 2024
© Institute of Computing Technology, Chinese Academy of Sciences 2024