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 to the design of neural network architectures. Recent works explored learning either global or local features or both for point clouds, however none of the earlier methods focused on capturing contextual shape information by analysing local orientation distribution of points. In this paper, we leverage on 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 by not only the selected point's nearest neighbors, but also 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 involves 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 S3DIS datasets.
翻译:3D点云的学习新表达方式是3D愿景中一个积极的研究领域,因为定点中点云结构仍然对神经网络结构的设计构成挑战。最近的工作探索了为点云学习全球或地方特征或两者,然而,早期的方法中没有一个侧重于通过分析点的局部方向分布来捕捉背景形状信息。在本文中,我们利用点方向分布在一个点周围的点,以获得点云的显性地方邻居代表。我们通过将指定点的球形周围分为预先定义的锥形体体体体体积来实现这一点,并且每个卷内的统计数据都用作点特征。这样,一个本地补丁不仅可以代表选定点的近邻,还可以代表点周围多个方向的点密度分布。然后,我们就可以建立一个方向分布功能(ODF)神经网络,其中涉及依赖 mlp (多层的多层偏移) 的ODFNet 模型, 新的 ODFNet 模型实现了模型在模型40 和 Scir ObjectNSDIS 数据设置上的目标分类的状态精确度。