Point cloud data have been widely explored due to its superior accuracy and robustness under various adverse situations. Meanwhile, deep neural networks (DNNs) have achieved very impressive success in various applications such as surveillance and autonomous driving. The convergence of point cloud and DNNs has led to many deep point cloud models, largely trained under the supervision of large-scale and densely-labelled point cloud data. Unsupervised point cloud representation learning, which aims to learn general and useful point cloud representations from unlabelled point cloud data, has recently attracted increasing attention due to the constraint in large-scale point cloud labelling. This paper provides a comprehensive review of unsupervised point cloud representation learning using DNNs. It first describes the motivation, general pipelines as well as terminologies of the recent studies. Relevant background including widely adopted point cloud datasets and DNN architectures is then briefly presented. This is followed by an extensive discussion of existing unsupervised point cloud representation learning methods according to their technical approaches. We also quantitatively benchmark and discuss the reviewed methods over multiple widely adopted point cloud datasets. Finally, we share our humble opinion about several challenges and problems that could be pursued in future research in unsupervised point cloud representation learning. A project associated with this survey has been built at https://github.com/xiaoaoran/3d_url_survey.
翻译:点云数据由于其在各种逆境下的卓越准确性和健壮性而被广泛探索。同时,深度神经网络 (DNN) 在各种应用领域,如监控和自动驾驶等方面取得了非常显著的成功。点云和 DNN 的融合导致了许多深度点云模型,这些模型主要是在大规模和密集标注的点云数据的监督下进行训练的。无监督的点云表示学习旨在从未标记的点云数据中学习通用和有用的点云表示,最近引起了越来越多的关注,这是由于大规模点云标注的约束。本文全面回顾了使用深度神经网络进行无监督点云表示学习的方法。首先描述了最近研究的动机、一般流程以及术语。然后简要介绍了相关背景,包括广泛采用的点云数据集和 DNN 架构。接着,在它们的技术方法下,对现有的无监督点云表示学习方法进行了广泛的讨论。我们还基于多种广泛采用的点云数据集对回顾的方法进行了量化评估和讨论。最后,我们分享了一些未来研究中可以追求的挑战和问题。与这项调查相关的一个项目已经在 https://github.com/xiaoaoran/3d_url_survey 上建立。