Point cloud patterns are hard to learn because of the implicit local geometry features among the orderless points. In recent years, point cloud representation in 2D space has attracted increasing research interest since it exposes the local geometry features in a 2D space. By projecting those points to a 2D feature map, the relationship between points is inherited in the context between pixels, which are further extracted by a 2D convolutional neural network. However, existing 2D representing methods are either accuracy limited or time-consuming. In this paper, we propose a novel 2D representation method that projects a point cloud onto an ellipsoid surface space, where local patterns are well exposed in ellipsoid-level and point-level. Additionally, a novel convolutional neural network named EllipsoidNet is proposed to utilize those features for point cloud classification and segmentation applications. The proposed methods are evaluated in ModelNet40 and ShapeNet benchmarks, where the advantages are clearly shown over existing 2D representation methods.

翻译：由于无序点之间隐含的局部几何特征,因此很难了解点云模式。近年来,2D空间的点云表示吸引了越来越多的研究兴趣,因为它暴露了2D空间的局部几何特征。通过将这些点投射为2D地貌图,各点之间的关系在像素之间传承下来,由2D进化神经网络进一步提取。但是,现有的2D代表方法要么准确性有限,要么耗时。在本文中,我们提出了一个新的 2D 代表方法,将点云投射到一个阴极地表空间,当地模式在光线层一级和点一级都非常暴露。此外,建议建立一个名为 Ellipsoidal Net 的新型革命性神经网络,利用这些特征进行点云分类和分化应用。在模型Net40 和 ShapeNet 基准中评估了拟议方法,这些方法的优点明显可见于现有的2D代表方法。