Analyzing the geometric and semantic properties of 3D point clouds through
the deep networks is still challenging due to the irregularity and sparsity of
samplings of their geometric structures. This paper presents a new method to
define and compute convolution directly on 3D point clouds by the proposed
annular convolution. This new convolution operator can better capture the local
neighborhood geometry of each point by specifying the (regular and dilated)
ring-shaped structures and directions in the computation. It can adapt to the
geometric variability and scalability at the signal processing level. We apply
it to the developed hierarchical neural networks for object classification,
part segmentation, and semantic segmentation in large-scale scenes. The
extensive experiments and comparisons demonstrate that our approach outperforms
the state-of-the-art methods on a variety of standard benchmark datasets (e.g.,
ModelNet10, ModelNet40, ShapeNet-part, S3DIS, and ScanNet).

本研究提出一种新的卷积方式，能够直接在 3D 点云上进行计算，并利用其环形结构捕捉每个点的局部邻域几何特征，通过应用于神经网络，实现了目标分类、部件分割和语义分割等任务，并在多个标准基准数据集上取得了比同类算法更好的结果。