基于多尺度图卷积的点云分类网络

近些年,越来越多有关深度学习的方法应用到了点云分类领域。文章提出一种基于多尺度图卷积的点云分类网络,通过获取不同范围内等间隔采样的k个邻近点,以搭建不同尺度的图卷积模块来学习多尺度局部特征。实验表明,该网络在ModelNet40数据集上的准确率达到了92.8%,具有较好的性能。

In recent years,more and more depth learning about the method is applied to the point cloud classification fields.This paper presents a point cloud classification network based on multi-scale graph convolution,and by obtaining the k neighboring points equidistant sampling in the different ranges,establishes graph convolution module of different scales learn multi-scale local features.The experiment shows that the accuracy of the network on the data set ModelNet40 reached 92.8%,with a good performance.