《计算机应用》唯一官方网站 ›› 2025, Vol. 45 ›› Issue (12): 3957-3963.DOI: 10.11772/j.issn.1001-9081.2024111617

• 多媒体计算与计算机仿真 • 上一篇    下一篇

基于自适应特征提取和特征融合的点云滤波

李维刚1,2, 王栋1, 王永强2, 李金灵2   

  1. 1.武汉科技大学 人工智能与自动化学院,武汉 430081
    2.武汉科技大学 冶金自动化检测技术教育部工程研究中心,武汉 430081
  • 收稿日期:2024-11-14 修回日期:2025-03-03 接受日期:2025-03-04 发布日期:2025-03-21 出版日期:2025-12-10
  • 通讯作者: 王栋
  • 作者简介:李维刚(1977—),男,湖北咸宁人,教授,博士,主要研究方向:工业过程控制、人工智能、机器学习
    王栋(2001—),男,湖北孝感人,硕士研究生,主要研究方向:点云滤波、深度学习
    王永强(1994—),男,河南许昌人,博士研究生,主要研究方向:点云智能处理
    李金灵(1996—),男,湖北咸宁人,博士研究生,主要研究方向:计算机视觉。
  • 基金资助:
    湖北省科技人才服务企业项目(202400288)

Point cloud filtering based on adaptive feature extraction and feature fusion

Weigang LI1,2, Dong WANG1, Yongqiang WANG2, Jinling LI2   

  1. 1.College of Artificial Intelligence and Automation,Wuhan University of Science and Technology,Wuhan Hubei 430081,China
    2.Engineering Research Center for Metallurgical Automation and Measurement Technology,Ministry of Education,Wuhan University of Science and Technology,Wuhan Hubei 430081,China
  • Received:2024-11-14 Revised:2025-03-03 Accepted:2025-03-04 Online:2025-03-21 Published:2025-12-10
  • Contact: Dong WANG
  • About author:LI Weigang, born in 1977, Ph. D., professor. His research interests include industrial process control, artificial intelligence, machine learning.
    WANG Dong, born in 2001, M. S. candidate. His research interests include point cloud filtering, deep learning.
    WANG Yongqiang, born in 1994, Ph. D. candidate. His research interests include intelligent processing of point clouds.
    LI Jinling, born in 1996, Ph. D. candidate. His research interests include computer vision.
  • Supported by:
    Hubei Provincial Science and Technology Talent Service Enterprise Project(202400288)

摘要:

针对现有滤波方法在处理具有高复杂度几何结构的点云模型中存在特征模糊现象,导致最终滤波效果较差的问题,设计一种基于自适应特征提取和特征融合策略的点云滤波网络PFRNet(Point cloud Feature Regularization fusion Network)。首先,通过自适应空间特征提取器学习不同邻域之间的特征信息,从而捕获不同维度的局部邻域特征,减少局部细节的丢失;其次,通过局部特征正则化融合从点云的局部信息中引入全局双线性响应,并对它进行正则化融合,削弱点云的共性特征,增强尖锐特征;最后,通过自相关注意力解码器在解码过程中增强不同邻域之间的联系,提升模型的全局感知能力,以更好地提取局部几何特征。实验结果表明,与Pointfilter相比,PFRNet的倒角距离(CD)和均方误差(MSE)分别降低了7.45%、4.99%;可视化结果显示,PFRNet相较于其他方法能够生成更接近真实的点云模型。

关键词: 点云滤波, 局部特征, 动态图边卷积, 特征融合, 注意力机制

Abstract:

Concerning the limitations of existing filtering methods in dealing with point cloud models with high complex geometric structure, where feature blurring artifacts degrade filtering performance, a point cloud filtering network based on adaptive feature extraction and feature fusion strategy named PFRNet (Point cloud Feature Regularization fusion Network) was proposed. Firstly, the feature information between different neighborhoods was learned by the adaptive spatial feature extractor, so as to capture the local neighborhood features of different dimensions and reduce the loss of local details. Then, the global bilinear response was introduced from the local information of the point cloud through the local feature regularized fusion, and it was regularized and fused to weaken the common features of the point cloud and enhance the sharp features. Finally, the self-correlation attention decoder was used to enhance the connection between different neighborhoods in the decoding process, improve the global perception ability of the model, and better extracting local geometric features. Experimental results show that compared with Pointfilter, PFRNet reduces Chamfering Distance (CD) and Mean Square Error (MSE) of 7.45% and 4.99%,respectively. Visualization results further confirm that PFRNet generates a point cloud model closer to the real one than other methods.

Key words: point cloud filtering, local feature, dynamic graph edge convolution, feature fusion, attention mechanism

中图分类号: