In this paper, we present a comprehensive point cloud semantic segmentation network that aggregates both local and global multi-scale information. First, we propose an Angle Correlation Point Convolution (ACPConv) module to effectively learn the local shapes of points. Second, based upon ACPConv, we introduce a local multi-scale split (MSS) block that hierarchically connects features within one single block and gradually enlarges the receptive field which is beneficial for exploiting the local context. Third, inspired by HRNet which has excellent performance on 2D image vision tasks, we build an HRNet customized for point cloud to learn global multi-scale context. Lastly, we introduce a point-wise attention fusion approach that fuses multi-resolution predictions and further improves point cloud semantic segmentation performance. Our experimental results and ablations on several benchmark datasets show that our proposed method is effective and able to achieve state-of-the-art performances compared to existing methods.
翻译:在本文中,我们展示了一个综合本地和全球多尺度信息的综合点云语系分化网络。 首先,我们提议了一个星际关联点变异模块(ACPConv),以有效学习本地点的形状。 其次,基于非加太国家同化,我们引入了一个本地多尺度分化块,将单个区块的特征分等级地连接在一起,并逐步扩大有利于利用本地环境的可接受域。第三,在具有2D图像任务出色性能的HRNet的启发下,我们为点云专门设计了一个HRNet,以学习全球多尺度背景。最后,我们引入了一种点性注意聚合法,将多分辨率预测结合起来,并进一步改进点云层分化性表现。我们的实验结果和几个基准数据集的汇总表明,我们拟议的方法是有效的,并且能够实现与现有方法相比的状态性表现。