LiDAR sensors are an integral part of modern autonomous vehicles as they provide an accurate, high-resolution 3D representation of the vehicle's surroundings. However, it is computationally difficult to make use of the ever-increasing amounts of data from multiple high-resolution LiDAR sensors. As frame-rates, point cloud sizes and sensor resolutions increase, real-time processing of these point clouds must still extract semantics from this increasingly precise picture of the vehicle's environment. One deciding factor of the run-time performance and accuracy of deep neural networks operating on these point clouds is the underlying data representation and the way it is computed. In this work, we examine the relationship between the computational representations used in neural networks and their performance characteristics. To this end, we propose a novel computational taxonomy of LiDAR point cloud representations used in modern deep neural networks for 3D point cloud processing. Using this taxonomy, we perform a structured analysis of different families of approaches. Thereby, we uncover common advantages and limitations in terms of computational efficiency, memory requirements, and representational capacity as measured by semantic segmentation performance. Finally, we provide some insights and guidance for future developments in neural point cloud processing methods.

翻译：激光雷达传感器是现代自动驾驶车辆不可或缺的组成部分，它能够提供车辆周围环境精准、高分辨率的三维表示。然而，利用来自多个高分辨率激光雷达传感器日益增长的数据量在计算上具有挑战性。随着帧率、点云规模和传感器分辨率的提升，对这些点云进行实时处理时，仍需从车辆环境日益精确的描绘中提取语义信息。影响作用于点云的深度神经网络运行性能与准确性的一个关键因素，是底层数据表示及其计算方式。本研究探讨了神经网络中使用的计算表示与其性能特征之间的关系。为此，我们提出了一种新颖的计算分类法，用于对现代深度神经网络中用于三维点云处理的激光雷达点云表示进行分类。基于该分类法，我们对不同类别的方法进行了结构化分析，从而揭示了它们在计算效率、内存需求以及以语义分割性能衡量的表示能力方面共有的优势与局限性。最后，我们为未来神经点云处理方法的发展提供了一些见解与指导。