Learning from 3D point-cloud data has rapidly gained momentum, motivated by the success of deep learning on images and the increased availability of 3D data. In this paper, we aim to construct anisotropic convolutions that work directly on the surface derived from a point cloud. This is challenging because of the lack of a global coordinate system for tangential directions on surfaces. We introduce a new convolution operator called DeltaConv, which combines geometric operators from exterior calculus to enable the construction of anisotropic filters on point clouds. Because these operators are defined on scalar- and vector-fields, we separate the network into a scalar- and a vector-stream, which are connected by the operators. The vector stream enables the network to explicitly represent, evaluate, and process directional information. Our convolutions are robust and simple to implement and show improved accuracy compared to state-of-the-art approaches on several benchmarks, while also speeding up training and inference.
翻译:从 3D 点球数据 中学习的3D 点球数据迅速获得动力,其动力来自对图像的深层次学习的成功和3D数据的提供量的增加。在本文中,我们的目标是构建直接对从点云中产生的表面工作的动脉变异。这具有挑战性,因为缺乏一个全球表层正向协调系统。我们引入了一个新的变形操作员Delta Conv, 它将外部微积分的几何操作员结合起来,以便能够在点云上建造动脉变异过滤器。由于这些操作员是用星标和矢量场来定义的,我们把网络分为一个由操作员连接的星标和矢量流。矢量流使网络能够明确代表、评估和处理方向信息。我们的变形过程是强大和简单的,可以执行和显示比若干基准的状态方法更精确性,同时加快培训和推断。