Point clouds data, as one kind of representation of 3D objects, are the most primitive output obtained by 3D sensors. Unlike 2D images, point clouds are disordered and unstructured. Hence it is not straightforward to apply classification techniques such as the convolution neural network to point clouds analysis directly. To solve this problem, we propose a novel network structure, named Attention-based Graph Convolution Networks (AGCN), to extract point clouds features. Taking the learning process as a message propagation between adjacent points, we introduce an attention mechanism to AGCN for analyzing the relationships between local features of the points. In addition, we introduce an additional global graph structure network to compensate for the relative information of the individual points in the graph structure network. The proposed network is also extended to an encoder-decoder structure for segmentation tasks. Experimental results show that the proposed network can achieve state-of-the-art performance in both classification and segmentation tasks.

中文翻译：

---

基于注意力的图卷积网络的点云学习

点云数据作为 3D 对象的一种表示，是 3D 传感器获得的最原始的输出。与 2D 图像不同，点云是无序和非结构化的。因此，将卷积神经网络等分类技术直接应用于点云分析并不简单。为了解决这个问题，我们提出了一种新的网络结构，称为基于注意力的图卷积网络（AGCN），用于提取点云特征。将学习过程作为相邻点之间的消息传播，我们向 AGCN 引入了一种注意力机制，用于分析点的局部特征之间的关系。此外，我们引入了一个额外的全局图结构网络来补偿图结构网络中各个点的相关信息。所提出的网络还扩展到用于分割任务的编码器-解码器结构。实验结果表明，所提出的网络在分类和分割任务中都可以达到最先进的性能。