Collecting accurate outdoor point cloud data depends on complex algorithms and expensive experimental equipment. The requirement of data collecting and the characteristics of point clouds limit the development of semantic segmentation technology in point clouds. Therefore, this paper proposes a neural network model named PointCartesian-Net that uses only 3D coordinates of point cloud data for semantic segmentation. First, to increase the feature information and reduce the loss of geometric information, the 3D coordinates are encoded to establish a connection between neighboring points. Second, a dense connect and residual connect are employed to progressively increase the receptive field for each 3D point, and aggregated multi-level and multi-scale semantic features obtain rich contextual information. Third, inspired by the success of the SENet model in 2D images, a 3D SENet that learns the relation between the characteristic channels is proposed. It allows the PointCartesian-Net to weight the informative features while suppressing less useful ones. The experimental results produce 60.2% Mean Intersection-over-Union and 89.1% overall accuracy on the large-scale benchmark Semantic3D dataset, which shows the feasibility and applicability of the network.

中文翻译：

---

PointCartesian-Net：增强用于大规模点云语义分割的 3D 坐标

收集准确的室外点云数据依赖于复杂的算法和昂贵的实验设备。数据采集​​的要求和点云的特性限制了点云语义分割技术的发展。因此，本文提出了一种名为PointCartesian-Net的神经网络模型，该模型仅使用点云数据的3D坐标进行语义分割。首先，为了增加特征信息，减少几何信息的丢失，对3D坐标进行编码，建立相邻点之间的连接。其次，采用密集连接和残差连接逐步增加每个 3D 点的感受野，聚合多级和多尺度语义特征获得丰富的上下文信息。第三，受 SENet 模型在 2D 图像中的成功启发，提出了一种学习特征通道之间关系的 3D SENet。它允许 PointCartesian-Net 对信息特征进行加权，同时抑制不太有用的特征。实验结果在大规模基准 Semantic3D 数据集上产生了 60.2% 的 Mean Intersection-over-Union 和 89.1% 的整体准确率，这表明了该网络的可行性和适用性。