基于可分离Transformer的点云分类方法

刘诚辉; 李光平

doi:10.12052/gdutxb.240003

欢迎来到能源电力期刊网！

English Version 期刊登录

您当前的位置：

首页 >

文章列表页 >

基于可分离Transformer的点云分类方法

计算机科学与技术 | 更新时间：2026-05-27

- 基于可分离Transformer的点云分类方法
- Point Cloud Classification Based on Separable Transformer
- 广东工业大学学报 2025年42卷第2期页码：29-36, 80
- 作者机构：
  
  广东工业大学信息工程学院,广东,广州,510006
- 作者简介：
  
  刘诚辉(1997–) ，男，硕士研究生，主要研究方向为3D点云处理、特征提取、点云分类，E-mail：1152278768@qq.com
  李光平(1981–)，男，副教授，博士，主要研究方向为计算机视觉、人工智能、雷达信号处理，E-mail：gpli@gdut.edu.cn
- 基金信息：
  
  国家自然科学基金资助项目(61601130);大亚湾科技规划项目(2020010203)
- DOI：10.12052/gdutxb.240003
  中图分类号： TP302.7
- 纸质出版：2025
- 稿件说明：
移动端阅览
刘诚辉, 李光平. 基于可分离Transformer的点云分类方法[J]. 广东工业大学学报, 2025, 42(2): 29–36.

Liu Chenghui, Li Guangping. Point Cloud Classification Based on Separable Transformer[J]. 2025, 42(2): 29-36, 80.
刘诚辉, 李光平. 基于可分离Transformer的点云分类方法[J]. 广东工业大学学报, 2025, 42(2): 29–36. DOI： 10.12052/gdutxb.240003

Liu Chenghui, Li Guangping. Point Cloud Classification Based on Separable Transformer[J]. 2025, 42(2): 29-36, 80. DOI： 10.12052/gdutxb.240003.

摘要

Transformer往往利用捕获远程依赖项的优势来提取点云远程点的关系交互，忽略重要的局部结构细节，并且依赖于大量的计算成本来实现高性能，导致计算负担增加。为了缓解这个问题，本文借鉴可分离视觉Transformer的思想，提出了一种可分离的Transformer点云分类方法，简称Sep-point。Sep-point通过深度可分离的自注意，帮助在点云组内和组间按顺序进行局部−全局关系交互。采用新的位置令牌嵌入和分组自注意方法，分别以可忽略的代价计算组间的注意关系，并建立跨多个区域的远程信息交互。提取局部−全局特征的同时，大大减少了计算负担。实验结果表明提出的Sep-point在数据集ModelNet40上比现有的PCT(Point Cloud Transformer)分类精度提升了0.2%，在真实数据集ScanObjectNN上的分类精度提升了6.3%。同时网络参数量和FLOPS指标分别降低了0.72M和0.18G，充分验证了本文方法的有效性。

Abstract

Transformer tends to take advantage of capturing remote dependencies to extract relational interactions at remote points of the point cloud

ignoring important local structural details

and achieves high performance by significantly increasing the computational burden. To alleviate this problem

we propose a separable Transformer point cloud classification method

named Sep-point

based on the idea of separable visual Transformer. The proposed Sep-point facilitates sequential local-global relational interactions within and between groups of point clouds through depth-separable self-attention. New location token embedding and group self-attention methods are used to compute inter-group attentional relationships with negligible computational cost and to establish telematic interactions across multiple regions

respectively. In this way

the local-global features are extracted while the computational burden is significantly reduced. Experimental results show that the proposed Sep-point improves the classification accuracy by 0.2% on the ModelNet40 dataset over the existing PCT (Point Cloud Transformer) and by 6.3% on the real ScanObjectNN dataset

respectively. Moreover

the number of network parameters and FLOPS metrics are reduced by 0.72M and 0.18G

respectively. These experimental results clearly demonstrate the promising effectiveness of our proposed method.

关键词

Keywords

references

SHI S, WANG X, LI H. PointRCNN: 3D object proposal generation and detection from point cloud[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach: IEEE, 2019: 770-779.

VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems. Long Beach: ACM, 2017: 6000-6010.

RAO Y, LU J , ZHOU J. Spherical fractal convolutional neural networks for point cloud recognition[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach: IEEE, 2019: 452-460.

YI L, SU H, GUO X, et al. Syncspeccnn: synchronized spectral CNN for 3D shape segmentation[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017: 6584-6592.

ZHANG Z, LI K, YIN X, et al . Point cloud semantic scene segmentation based on coordinate convolution [J ] . Computer Animation and Virtual Worlds, 2020, 31(4-5): e1948.

SHI S, WANG Z, SHI J, et al . From points to parts: 3D object detection from point cloud with part-aware and part-aggregation network [J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 43(8): 2647-2664.

PENG L, LIU F, YU Z, et al. Lidar point cloud guided monocular 3D object detection[C]//2022 European Conference on Computer Vision. Tel Aviv: Springer, 2022: 123-139.

YANG H, SHI J, CARLONE L. Teaser: fast and certifiable point cloud registration [J]. IEEE Transactions on Robotics, 2020, 37(2): 314-333.

GUO M, CAI J, LIU Z, et al . PCT: point cloud transformer [J ] . Computational Visual Media, 2021, 7(2): 187-199.

ZHAO H, JIANG L, JIA J, et al . Point transformer [J ] . IEEE Access, 2021, 9(3): 16259-16268.

WANG Z, LU F. VoxSegNet: volumetric CNNs for semantic part segmentation of 3D shapes [J]. IEEE Transactions on Visualization and Computer Graphics, 2019, 26(9): 2919-2930.

SHI S, GUO C, JIANG L, et al. PV-RCNN: point-voxel feature set abstraction for 3D object detection[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020: 10526-10535.

QI C, SU H, MO K, et al. PointNet: deep learning on point sets for 3D classification and segmentation[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017: 77-85.

QI C, YI L, SU H, et al. PointNet++: deep hierarchical feature learning on point sets in a metric space[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems. Long Beach: ACM, 2017: 5105–5114.

LI Y, BU R, SUN M, et al. PointCNN: convolution on x-transformed points[C]//Proceedings of the 32nd International Conference on Neural Information Processing Systems. Montréal: ACM, 2018: 828-838.

LIU X, HAN Z, LIU Y, et al. Point2sequence: learning the shape representation of 3D point clouds with an attention-based sequence to sequence network[C]//Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence and Thirty-First Innovative Applications of Artificial Intelligence Conference and Ninth AAAI Symposium on Educational Advances in Artificial Intelligence. Honolulu: AAAI, 2019, 33: 8778-8785.

WANG Y, SUN Y, LIU Z, et al . Dynamic graph CNN for learning on point clouds [J ] . ACM Transactions on Graphics, 2019, 38(5): 1-12.

WU W, QI Z, Li F. PointConv: deep convolutional networks on 3D point clouds[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach: IEEE, 2019: 9613-9622.

THOMAS H, QI C, DESCHAUD J, et al. KPConv: flexible and deformable convolution for point clouds[C]//2019 IEEE/CVF International Conference on Computer Vision. Seoul: IEEE, 2019: 6410-6419.

XU M, DING R, ZHAO H, et al. PAConv: position adaptive convolution with dynamic kernel assembling on point clouds[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville: IEEE, 2021: 3172-3181.

LANDRIEU L, BOUSSAHA M. Point cloud oversegmentation with graph-structured deep metric learning[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach: IEEE, 2019: 7432-7441.

WU Z, SONG S, KHOSLA A, et al. 3D ShapeNets: a deep representation for volumetric shapes[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition. Boston: IEEE, 2015: 1912-1920.

UY M, PHAM Q, HUA B, et al. Revisiting point cloud classification: a new benchmark dataset and classification model on real-world data[C]//2019 IEEE/CVF International Conference on Computer Vision. Seoul: IEEE, 2019: 1588-1597.

XU Y, FAN T, XU M, et al. SpiderCNN: deep learning on point sets with parameterized convolutional filters[C]//Computer Vision-ECCV 2018. Munich: Springer, 2018: 99-105.

LIU Y, FAN B, XIANG S, et al. Relation-shape convolutional neural network for point cloud analysis[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach: IEEE, 2019: 8887-8896.

YAN X, ZHENG C, LI Z, et al. PointASNL: robust point clouds processing using nonlocal neural networks with adaptive sampling[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020: 5588-5597.

QIU S, ANWAR S, BARNES N. Dense-resolution network for point cloud classification and segmentation[C]//2021 IEEE Winter Conference on Applications of Computer Vision, Waikoloa: IEEE, 2021: 3812-3821.

QIU S, ANWAR S, BARNES N. Geometric back-projection network for point cloud classification [J]. IEEE Transactions on Multimedia, 2021, 24(3): 1943-1955.

GOYAL A, LAW H, LIU B, et al. Revisiting point cloud shape classification with a simple and effective baseline[C]//Proceedings of the 38th International Conference on Machine Learning. Vienna: IMLS, 2021: 3809-3820.

HAMDI A, GIANCOLA S, GHANEM B. MVTN: multi-view transformation network for 3D shape recognition[C]//2021 IEEE/CVF International Conference on Computer Vision. Montreal: IEEE, 2021: 1-11.

YU X, TANG L, RAO Y, et al. Point-BERT: pre-training 3D point cloud transformers with masked point modeling[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New Orleans: CVPR, 2022: 19291-19300.

CHENG S, CHEN X, HE X, et al . PRA-Net: point relation-aware network for 3D point cloud analysis [J ] . IEEE Transactions on Image Processing, 2021, 30(2): 4436-4448.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于PSI技术的福州市地面形变监测与影响因素分析

基于高效时序建模的RGB-T跟踪

人工噪声辅助无人机太赫兹安全通信的鲁棒设计

具守恒量波动方程的循环双子网物理信息神经网络

融合沟道倾斜角的3D NAND存储单元建模及编程策略优化