Point cloud has drawn more and more research attention as well as real-world applications. However, many of these applications (e.g. autonomous driving and robotic manipulation) are actually based on sequential point clouds (i.e. four dimensions) because the information of the static point cloud data could provide is still limited. Recently, researchers put more and more effort into sequential point clouds. This paper presents an extensive review of the deep learning-based methods for sequential point cloud research including dynamic flow estimation, object detection \& tracking, point cloud segmentation, and point cloud forecasting. This paper further summarizes and compares the quantitative results of the reviewed methods over the public benchmark datasets. Finally, this paper is concluded by discussing the challenges in the current sequential point cloud research and pointing out insightful potential future research directions.
Registration between Point Cloud Streams and Sequential Bounding Boxes via Gradient Descent
Australia Nation University（澳大利亚国立大学）；Chinese University of Hong Kong（香港中文大学）；ShanghaiTech University（上海科技大学）；University of Sydney（悉尼大学）；University of New South Wales（新南威尔士大学）
GroundFlow: A Plug-in Module for Temporal Reasoning on 3D Point Cloud Sequential Grounding
Nanyang Technological University（南洋理工大学）；Centre for Frontier AI Research, A*STAR（前沿人工智能研究中心，A*STAR）；MoE Key Laboratory of Interdisciplinary Research of Computation and Economics, Shanghai University of Finance and Economics（计算与经济学交叉研究关键实验室，上海财经大学）
Deep Learning for 3D Point Cloud Enhancement: A Survey
School of Electronics and Control Engineering, Chang’an University（长安大学电子与控制工程学院）；School of Software Engineering, Northwestern Polytechnical University（西北工业大学软件学院）；School of Computer Science, Northwestern Polytechnical University（西北工业大学计算机学院）；School of Electronic Information and Communications, Huazhong University of Science and Technology（华中科技大学电子信息与通信学院）
Unsupervised Point Cloud Representation Learning with Deep Neural Networks: A Survey
Nanyang Technological University（南洋理工大学）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Wenzhou University（温州大学）；UCAS（中国科学院大学）
Point Cloud Compression and Objective Quality Assessment: A Survey
Cooperative Medianet Innovation Center, Shanghai Jiao Tong University（上海交通大学合作中位网创新中心）；University of Missouri–Kansas City（密苏里大学-堪萨斯城分校）；Department of Electrical and Computer Engineering, University of Canterbury（坎特伯雷大学电子与计算机工程系）
Sun Yat-sen University（中山大学）；Information Engineering University（信息工程大学）；University of Oxford（牛津大学）；National University of Defense Technology（国防科技大学）；University of Oulu（奥卢大学）；the University of Western Australia（西澳大学）
MSF: Motion-guided Sequential Fusion for Efficient 3D Object Detection from Point Cloud Sequences
The Hong Kong Polytechnic University（香港理工大学）
点云序列通常用于在自动驾驶等应用中准确检测3D对象。当前性能最高的多帧检测器大多遵循检测并融合框架，该框架从序列的每个帧中提取特征并融合它们以检测当前帧中的对象。然而，这不可避免地导致冗余计算，因为相邻帧是高度相关的。在本文中，我们提出了一种有效的运动引导顺序融合（MSF）方法，该方法利用对象运动的连续性来挖掘有用的顺序上下文，用于当前帧中的目标检测。我们首先在当前帧上生成3D建议，并根据估计的速度将它们传播到前面的帧。然后从序列中汇集兴趣点并编码为建议特征。提出了一种新的双向特征聚合（BiFA）模块，以促进跨框架的建议特征的交互。此外，我们优化点云池基于体素的采样技术，使数百万点可以在几毫秒内处理。提出的MSF方法不仅比其他多帧检测器具有更好的效率，而且准确率也领先，在Waymo Open Dataset的LEVEL1和LEVEL2测试集上分别获得83.12%和78.30%的mAP。代码可在\url{https://github.com/skyhehe123/MSF}上找到。
DetZero: Rethinking Offboard 3D Object Detection with Long-term Sequential Point Clouds
Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；East China Normal University（华东师范大学）；South China University of Technology（华南理工大学）；Fudan University（复旦大学）；ETH Zurich（苏黎世联邦理工学院）；The Chinese University of Hong Kong（香港中文大学）
本文提出 DetZero 离线 3D 检测范式，通过离线跟踪、多帧检测和注意力精炼融合长期点云，在 Waymo 上达到 85.15 mAPH（L2）并排名第一。
A Survey on Facial Image Privacy Preservation in Cloud-Based Services
Nanyang Technological University（南洋理工大学）；School of Cyber Science and Engineering, Wuhan University（武汉大学网络安全学院）；College of Electrical Engineering, Zhejiang University（浙江大学电气工程学院）
