VALSE 论文速览 第103期：以运动为导向的点云单目标跟踪范式

论文题目：Beyond 3D Siamese Tracking: A Motion-Centric Paradigm for 3D Single Object Tracking in Point Clouds

作者列表：郑超达 (香港中文大学(深圳))，颜旭 (香港中文大学(深圳))，张海鸣 (香港中文大学(深圳))，王宝元 (小冰AI)，成生辉 (西湖大学)，崔曙光 (香港中文大学(深圳))，李镇 (香港中文大学(深圳))

B站观看网址：

https://www.bilibili.com/video/BV1aG4y1V7wZ/

论文摘要：

3D single object tracking (3D SOT)in LiDAR point clouds plays a crucial role in autonomous driving. Current approaches all follow the Siamese paradigm based on appearance matching. However, LiDAR point clouds are usually textureless and incomplete, which hinders effective appearance matching. Besides, previous methods greatly overlook the critical motion clues among targets. In this work, beyond 3D Siamese tracking, we introduce a motion-centric paradigm to handle 3D SOT from a new perspective. Following this paradigm, we propose a matching-free two-stage tracker M2-Track. At the 1st -stage, M2 -Track localizes the target within successive frames via motion transformation. Then it refines the target box through motion-assisted shape completion at the 2nd -stage. Extensive experiments confirm that M2-Track significantly outperforms previous state-of-the-arts on three large-scale datasets while running at 57FPS (~8%, ~17% and ~22% precision gains on KITTI, NuScenes, and Waymo Open Dataset respectively). Further analysis verifies each component's effectiveness and shows the motion centric paradigm's promising potential when combined with appearance matching.

论文信息：

[1] Chaoda Zheng, Xu Yan, Haiming Zhang, Baoyuan Wang, Shenghui Cheng, Shuguang Cui, Zhen Li, Beyond 3D Siamese Tracking: A Motion-Centric Paradigm for 3D Single Object Tracking in Point Clouds In CVPR, 2022.

论文链接：

[https://arxiv.org/abs/2203.01730]

代码链接：

[https://github.com/Ghostish/Open3DSOT]

视频讲者简介：

郑超达，香港中文大学 (深圳)理工学院博士生。主要研究方向点云处理与分析。在CVPR，ICCV，ECCV，TIP等顶级期刊和会议发表多篇论文。

特别鸣谢本次论文速览主要组织者：

月度轮值AC：李冠彬 (中山大学)、李镇 (香港中文大学 (深圳))

季度责任AC：张姗姗 (南京理工大学)