A survey on end‐to‐end point cloud learning

Abstract

Point cloud is an important expression form of three‐dimensional (3D) data. It has enjoyed continuous development and attracted increasing attention due to its wide applications in many areas, such as artificial intelligence, deep learning, autonomous driving and tracking. Recently, there is a large number of end‐to‐end point cloud‐based deep learning methods being proposed which are successful in the 3D domain. In order to better use point cloud data for analysis and to explore future research directions, this paper presents a comprehensive review of existing methods and publicly available datasets, with a focus on the methods and research status of using point cloud data as direct input. The background of point cloud is first introduced, including data acquisition methods, basic concepts, and challenges. Following that, the deep learning methods based on point cloud data are investigated and analysed according to classification, detection and tracking, and segmentation. Furthermore, the existing public datasets and evaluation metrics are introduced. Finally, promising research directions are proposed in conjunction with existing methods.

Learnable interpolation and extrapolation network for fuzzy pulmonary lobe segmentation

“…PointNet [22] and its extension PointNet++ [23] are the pioneers in deep neural networks that operate on point clouds. The end-to-end structure, which means input data is original data, and output is final result, was very successful in the 3D domain [24]. Yuan et al [25] built a method upon PointNet to complete the shape by exploring deformable meshes as the shape representation.…”