光学精密工程2025，Vol.33Issue(5)：777-788,12.DOI:10.37188/OPE.20253305.0777
面向点云分类和分割的形状自适应特征聚合网络
Shape adaptive feature aggregation network for point cloud classification and segmentation
摘要
Abstract
The classification and segmentation of point clouds are widely applicable in robotic navigation,virtual reality,and autonomous driving.Most current deep learning approaches for point cloud processing employ multilayer perceptrons(MLPs)with shared weights and single pooling operations to aggregate lo-cal features.This methodology often hinders the accurate representation of structural information within point clouds exhibiting complex arrangements.To address these challenges,a novel point cloud shape-adaptive local feature encoding method was proposed,aimed at effectively capturing the structural informa-tion of point clouds with diverse geometric configurations while enhancing classification and segmentation performance.Initially,an adaptive feature enhancement module was introduced,this module utilized dif-ferentiation and learnable adjustment factors to strengthen the feature representation,compensating for the descriptive limitations inherent in shared weight MLPs.Building on this foundation,a feature aggregation module was designed to assign variable weights to distinct points based on their absolute spatial distances.This approach facilitates adaptation to the variable shapes of point cloud structures,accentuates representa-tive point sets,and enables a more precise depiction of local structural information.Experimental evalua-tions conducted on three extensive public point cloud datasets reveal that the proposed method achieves ex-ceptional performance in both classification and segmentation tasks,attaining an overall instance average classification accuracy of 93.9%on the ModelNet40 dataset,along with mean intersection over union(mIoU)scores of 85.9%and 59.7%on the ShapeNet and S3DIS datasets,respectively.关键词
深度学习/点云分类/点云分割/局部特征聚合Key words
deep learning/point cloud classification/point cloud segmentation/local feature aggregation分类
计算机与自动化引用本文复制引用
蒋志豪,张美香,薛卫涛,付莉娜,文静,李永强,黄鸿..面向点云分类和分割的形状自适应特征聚合网络[J].光学精密工程,2025,33(5):777-788,12.基金项目
国家自然科学基金资助项目(No.42071302) （No.42071302）
先进光学遥感技术北京市重点实验室开放基金资助项目(No.AORS202315) （No.AORS202315）
重庆市留学人员回国创业创新支持计划资助项目(No.cx2019144) （No.cx2019144）
