Learning new representations of 3D point clouds is an active research area in 3D vision, as the order-invariant point cloud structure still presents challenges for the design of neural network architectures. Recent work explored learning global, local, or multi-scale features for point clouds. However, none of the earlier methods focused on capturing contextual shape information by analyzing local orientation distributions of points. In this paper, we use point orientation distributions around a point in order to obtain an expressive local neighborhood representation for point clouds. We achieve this by dividing the spherical neighborhood of a given point into predefined cone volumes, and statistics inside each volume are used as point features. In this way, a local patch can be represented not only by the selected point’s nearest neighbors, but also by considering a point density distribution defined along multiple orientations around the point. We are then able to construct an orientation distribution function (ODF) neural network that makes use of an ODFBlock which relies on MLP (multi-layer perceptron) layers. The new ODFNet model achieves state-of-the-art accuracy for object classification on ModelNet40 and ScanObjectNN datasets, and segmentation on ShapeNet and S3DIS datasets.

学习 3D 点云的新表示是 3D 视觉中一个活跃的研究领域，因为顺序不变的点云结构仍然对神经网络架构的设计提出了挑战。最近的工作探索了学习点云的全局、局部或多尺度特征。然而，早期的方法都没有专注于通过分析点的局部方向分布来捕获上下文形状信息。在本文中，我们使用点周围的点方向分布来获得点云​​的富有表现力的局部邻域表示。我们通过将给定点的球形邻域划分为预定义的锥体来实现这一点，并且每个体积内的统计数据都用作点特征。这样，局部补丁不仅可以由所选点的最近邻居表示，还要考虑沿点周围多个方向定义的点密度分布。然后，我们能够构建一个方向分布函数 (ODF) 神经网络，该网络利用依赖于 MLP（多层感知器）层的 ODFBlock。新的 ODFNet 模型在 ModelNet40 和 ScanObjectNN 数据集上的对象分类以及在 ShapeNet 和 S3DIS 数据集上实现了最先进的精度。