当前位置: X-MOL 学术Multimedia Syst. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Direction-induced convolution for point cloud analysis
Multimedia Systems ( IF 3.5 ) Pub Date : 2021-03-23 , DOI: 10.1007/s00530-021-00770-0
Yuan Fang , Chunyan Xu , Chuanwei Zhou , Zhen Cui , Chunlong Hu

Point cloud analysis becomes a fundamental but challenging problem in the field of 3D scene understanding. To deal with unstructured and unordered point clouds in the embedded 3D space, we propose a novel direction-induced convolution (DIConv) to obtain the hierarchical representations of point clouds and then boost the performance of point cloud analysis. Specifically, we first construct a direction set as the basis of spatial direction information, where its entries can denote these latent direction components of 3D points. For each neighbor point, we can project its direction information into the constructed direction set for achieving an array of direction-dependent weights, then transform its features into the canonical ordered direction set space. After that, the standard image-like convolution can be leveraged to encode the unordered neighborhood regions of point cloud data. We further develop a residual DIConv (Res_DIConv) module and a farthest point sampling residual DIConv (FPS_Res_DIConv) module for jointly capturing the hierarchical features of input point clouds. By alternately stacking Res_DIConv modules and FPS_Res_DIConv modules, a direction-induced convolution network (DICNet) can be built to perform point cloud analysis in an end-to-end fashion. Comprehensive experiments on three benchmark datasets (including ModelNet40, ShapeNet Part, and S3DIS) demonstrate that the proposed DIConv method achieves encouraging performance on both point cloud classification and semantic segmentation tasks.



中文翻译:

方向感应卷积用于点云分析

点云分析已成为3D场景理解领域中一个基本但具有挑战性的问题。为了处理嵌入式3D空间中的非结构化和无序点云,我们提出了一种新颖的方向感应卷积(DIConv),以获得点云的分层表示形式,然后提高了点云分析的性能。具体来说,我们首先构造一个方向集作为空间方向信息的基础,其中其条目可以表示3D点的这些潜在方向分量。对于每个相邻点,我们可以将其方向信息投影到构造的方向集中,以实现与方向相关的权重数组,然后将其特征转换为规范的有序方向设置空间。之后,可以利用标准的类似图像的卷积来编码点云数据的无序邻域区域。我们进一步开发了残差DIConv(Res_DIConv)模块和最远点采样残差DIConv(FPS_Res_DIConv)模块,用于共同捕获输入点云的分层特征。通过交替堆叠Res_DIConv模块和FPS_Res_DIConv模块,可以构建方向感应卷积网络(DICNet)以端到端的方式执行点云分析。在三个基准数据集(包括ModelNet40,ShapeNet Part和S3DIS)上的综合实验表明,所提出的DIConv方法在点云分类和语义分割任务上均实现了令人鼓舞的性能。我们进一步开发了残差DIConv(Res_DIConv)模块和最远点采样残差DIConv(FPS_Res_DIConv)模块,以共同捕获输入点云的分层特征。通过交替堆叠Res_DIConv模块和FPS_Res_DIConv模块,可以构建方向感应卷积网络(DICNet)以端到端的方式执行点云分析。在三个基准数据集(包括ModelNet40,ShapeNet Part和S3DIS)上的综合实验表明,所提出的DIConv方法在点云分类和语义分割任务上均实现了令人鼓舞的性能。我们进一步开发了残差DIConv(Res_DIConv)模块和最远点采样残差DIConv(FPS_Res_DIConv)模块,用于共同捕获输入点云的分层特征。通过交替堆叠Res_DIConv模块和FPS_Res_DIConv模块,可以构建方向感应卷积网络(DICNet)以端到端的方式执行点云分析。在三个基准数据集(包括ModelNet40,ShapeNet Part和S3DIS)上的综合实验表明,所提出的DIConv方法在点云分类和语义分割任务上均实现了令人鼓舞的性能。可以构建方向感应卷积网络(DICNet)以端到端的方式执行点云分析。在三个基准数据集(包括ModelNet40,ShapeNet Part和S3DIS)上的综合实验表明,所提出的DIConv方法在点云分类和语义分割任务上均实现了令人鼓舞的性能。可以构建方向感应卷积网络(DICNet)以端到端的方式执行点云分析。在三个基准数据集(包括ModelNet40,ShapeNet Part和S3DIS)上的综合实验表明,所提出的DIConv方法在点云分类和语义分割任务上均实现了令人鼓舞的性能。

更新日期:2021-03-23
down
wechat
bug