基于隐藏特征的点云模块

邹舒航; 李光平; 高祥

doi:10.12052/gdutxb.240153

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 >

基于隐藏特征的点云模块

计算机科学与技术 | 更新时间：2026-05-27

- 基于隐藏特征的点云模块
- Point Cloud Module Based on Hidden Features
- 广东工业大学学报 2025年42卷第6期页码：62-69
- 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：
  
  邹舒航(1999–) ，男，硕士研究生，主要研究方向为点云处理、特征提取、点云分类，E-mail: 875936772@qq.com
  李光平(1981–) ，男，副教授，博士，主要研究方向为机器学习与信号处理，E-mail: gpli@gdut.edu.cn
- 基金信息：
  
  国家自然科学基金资助项目(61601130);大亚湾科技计划项目(2020010203)
- DOI：10.12052/gdutxb.240153
  中图分类号： TP394.1
- 纸质出版：2025
- 稿件说明：
移动端阅览
邹舒航, 李光平, 高祥. 基于隐藏特征的点云模块[J]. 广东工业大学学报, 2025, 42(6): 62–69.

Zou Shuhang, Li Guangping, Gao Xiang. Point Cloud Module Based on Hidden Features[J]. 2025, 42(6): 62-69.
邹舒航, 李光平, 高祥. 基于隐藏特征的点云模块[J]. 广东工业大学学报, 2025, 42(6): 62–69. DOI： 10.12052/gdutxb.240153

Zou Shuhang, Li Guangping, Gao Xiang. Point Cloud Module Based on Hidden Features[J]. 2025, 42(6): 62-69. DOI： 10.12052/gdutxb.240153.

摘要

点云全局特征和局部特征之间普遍存在隐藏特征，挖掘并利用隐藏特征可增强点云表示能力。但现有理论中，对隐藏特征的分析利用并不深入。为进一步挖掘利用隐藏特征，提出一种基于注意力机制的隐藏特征利用(Attention-based Hidden Feature Utilization，AHU)模块。模块由两部分子模块组成，一方面，基于通道注意力机制的子模块加强特征通道间的依赖关系，提升隐藏特征的显著性；另一方面，基于交叉注意力机制的子模块将学习到的隐藏特征反投影到原始局部特征上，并建立二者的长距离依赖关系，促进信息融合并提高模块泛化能力。本文拓展了隐藏特征的相关理论，并以实验证明，AHU模块可以集成到现有的先进网络中，显著提高其性能。

Abstract

Existing research has shown that there are hidden features between the global and local features of point cloud

and the representation capability of point cloud can be enhanced by mining and utilizing the hidden features. However

existing theories have not delved deeply into the analysis and utilization of hidden features. To further exploit the hidden features

we propose an Attention-based Hidden Feature Utilization (AHU) module

which consists of two sub-modules. On one hand

a sub-module based on channel attention mechanism enhances the inter-channel dependencies of features

improving the significance of hidden features; on the other hand

another sub-module based on cross-attention mechanism projects the learned hidden features back to the original local features

establishing long-distance dependencies between them and promoting information fusion

such that the generalization ability of the module can be improved. This paper extends the theory about hidden features and the experimental results demonstrate that the AHU module can be integrated into existing state-of-the-art networks to significantly improve the performance.

关键词

Keywords

references

WANG S, SUO S, MA W C, et al . Deep parametric continuous convolutional neural networks[C ] //Proceedings of the IEEE Conference on Computer Vision a nd Pattern Recognition. Salt Lake City: IEEE, 2018: 2589-2597.

DUAN H, WANG P, HUANG Y, et al . Robotics dexterous grasping: the methods based on point cloud and deep learning[J ] . Frontiers in Neurorobotics, 2021, 15: 658280.

TUZEL O, LIU M Y, TAGUCHI Y, et al . Learning to rank 3D features[C ] //Computer Vision–ECCV 2014: 13th European Conference. Zurich, Switzerland: Springer, 2014: 520-535.

QI C R, SU H, MO K, et al . Pointnet: deep learning on point sets for 3D classification and segmentation[C ] //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, USA: IEEE, 2017: 652-660.

QI C R, YI L, SU H, et al . Pointnet++: deep hierarchical feature learning on point sets in a metric space[J ] . Advances in Neural Information Processing Systems, 2017, 30: 5099-5108.

GUO Y, WANG H, HU Q, et al . Deep learning for 3D point clouds: a survey[J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 43(12): 4338-4364.

ZHAO H, JIANG L, FU C W, et al . Pointweb: enhancing local neighborhood features for point cloud processing[C ] //Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, USA: IEEE, 2019: 5565-5573.

ZHANG Y X, SUN Z L, ZENG Z, et al . Partial point cloud registration with deep local feature[J ] . IEEE Transactions on Artificial Intelligence, 2022, 4(5): 1317-1327.

HUI L, CHENG M, XIE J, et al . Efficient 3D point cloud feature learning for large-scale place recognition[J ] . IEEE Transactions on Image Processing, 2022, 31: 1258-1270.

CHEN J, ZHANG Y, MA F, et al . EB-LG module for 3D point cloud classification and segmentation[J ] . IEEE Robotics and Automation Letters, 2022, 8(1): 160-167.

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

NEZHADARYA E, TAGHAVI E, RAZANI R, et al . Adaptive hierarchical down-sampling for point cloud classification[C ] //Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020: 12956-12964.

LIU X, HAN Z , LIU Y S, et al . Point2sequence: learning the shape representation of 3D point clouds with an attention-based sequence to sequence network[C ] //Proceedings of the AAAI Conference on Artificial Intelligence. Honolulu, USA: IEEE, 2019: 8778-8785.

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

ZHAO H, JIANG L, JIA J, et al . Point transformer[C ] //Proceedings of the IEEE/CVF International Conference on Computer Vision. Nashville, USA: IEEE, 2021: 16259-16268.

HU J, SHEN L, SUN G. Squeeze-and-excitation networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 7132-7141.

NAIR V, HINTON G E. Rectified linear units improve restricted boltzmann machines[C]//Proceedings of the 27th International Conference on Machine Learning (ICML-10) . Haifa, Israel: IMLS, 2010: 807-814.

LIN H, CHENG X, WU X, et al . CAT: cross attention in vision transformer[C ] //2022 IEEE International Conference on Multimedia and Expo (ICME) . Taiwan, China: IEEE, 2022: 1-6.

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

UY M A, PHAM Q H, HUA B S, et al . Revisiting point cloud classification: a new benchmark dataset and classification model on real-world data[C ] //Proceedings of the IEEE/CVF International Conference on Computer Vision. Long Beach, USA: IEEE, 2019: 1588-1597.

QIAN G, LI Y, PENG H, et al . Pointnext: revisiting pointnet++ with improved training and scaling strategies[J ] . Advances in Neural Information Processing Systems, 2022, 35: 23192-23204.

LIU Y, TIAN B, LYU Y, et al . Point cloud classification using content-based transformer via clustering in feature space[J ] . IEEE/CAA Journal of Automatica Sinica, 2023, 11(1): 231-239.

WANG X, CHEN S, SU J. App-Net: a hybrid neural network for encrypted mobile traffic classification[C]//IEEE INFOCOM 2020-IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS) . Toronto: IEEE, 2020: 424-429.

TANG Y, LI X, XU J, et al . Point-LGMask: local and global contexts embedding for point clo ud pre-training with multi-ratio masking[J ] . IEEE Transactions on Multimedia, 2023, 26: 8360-8370.

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

基于注意力机制的无监督GAN多聚焦图像融合

多套餐共享储能模式下考虑功率互济的社区联盟优化运行策略

SCA-YOLO: 基于可变形卷积与上下文感知注意力的实时目标检测

基于AAGV-YOLOX模型的输电线路异物检测研究

储能变流器电能质量治理策略研究