IPFA-Net:Important Points Feature Aggregating Net for Point Cloud Classification and Segmentation  

作　　者：Jingya Wang Yu Zhang Bin Zhang Jinxiang Xia Weidong Wang 

机构地区：[1]School of Information and Software Engineering,University of Electronic Science and Technology of China,Chengdu 610054,China [2]National Key Laboratory of Automotive Chassis Integration and Bionics,Jilin University,Changchun 130012,China

出　　处：《Chinese Journal of Electronics》2025年第1期322-337,共16页电子学报(英文版)

基　　金：supported by the Sichuan Province Science and Technology Support Program(Grant No.2021YFQ0054);the Open Project Fund of Intelligent Terminal Key Laboratory of Sichuan Province(2020–2021)(Grant No.SCITLAB-0012)。

摘　　要：This paper focuses on the problems of point cloud deep neural networks in classification and segmentation tasks,including losing important information during down-sampling,ignoring relationships among points when extracting features,and network performance being susceptible to the sparsity of point cloud.To begin with,this paper proposes a farthest point sampling-important points sampling method for down-sampling,which can preserve important information of point clouds and maintain the geometry of input data.Then,the local feature relation aggregating method is proposed for feature extraction,improving the network's ability to learn contextual information and extract rich local region features.Based on these methods,the important points feature aggregating net(IPFA-Net)is designed for point cloud classification and segmentation tasks.Furthermore,this paper proposes the multi-scale multi-density feature connecting method to reduce the negative impact of point cloud data sparsity on network performance.Finally,the effectiveness of IPFA-Net is demonstrated through experiments on ModelNet40,ShapeNet part,and ScanNet v2 datasets.IPFA-Net is robust to reducing the number of point clouds,with only a 3.3%decrease in accuracy under a 16-fold reduction of point number.In the part segmentation experiments,our method achieves the best segmentation performance for five objects.

关 键 词：Deep learning Point clouds DOWN-SAMPLING Feature extraction 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]