计算机工程2025，Vol.51Issue(6)：146-154,9.DOI:10.19678/j.issn.1000-3428.0069284
融合可变形核和自注意力的点云分类分割边卷积网络
Edge Convolutional Network for Point Cloud Classification and Segmentation Incorporated Deformable Kernel and Self-Attention
摘要
Abstract
Owing to the unordered and discrete nature of point cloud data,traditional dynamic graph convolution method faces significant challenges in processing this data,making it difficult to accurately represent feature correspondences between 3D points.To address this issue,a network called DKSA-Net is proposed,which incorporates deformable kernels and self-attention.This network consists of two main modules:Deformable Kernels edge Convolution(DKConv)and Self-Attention edge Convolution(SAConv).By integrating deformable kernels with edge convolution to construct the DKConv module,the network can dynamically learn point features,generate deformable kernels,and maintain feature correspondences,thereby improving the handling of feature correspondences.In addition,by introducing the self-attention mechanism and combining it with edge convolution to construct the SAConv module,the network can perform finer-grained feature extraction,fully capture important point cloud features,and enhance the discriminative ability of the model.The experimental results show that DKSA-Net achieves excellent performance on the ModelNet40 and ShapeNet datasets,with an Overall Accuracy(OA)of 93.4％,an average Accuracy(mAcc)of 90.7％,and an average Intersection-over-Union(mIoU)of 86.1％.Furthermore,it demonstrates relatively low model complexity and high robustness,showcasing exceptional capabilities in processing point cloud data.关键词
可变形核/自注意力/点云分类/点云分割/深度学习Key words
deformable kernel/self-attention/point cloud classification/point cloud segmentation/deep learning分类
信息技术与安全科学引用本文复制引用
陈思帆,杨家志,黄琳,吕志玮,沈露..融合可变形核和自注意力的点云分类分割边卷积网络[J].计算机工程,2025,51(6):146-154,9.基金项目
国家自然科学基金(62166012). （62166012）
