Existing 3D single object trackers (SOTs) of a point cloud all apply downscaling when extracting features from points. This operation leads to a loss of spatial and structural information, degrading tracking performance of sparsely distributed and small-scale objects. To address this problem, a structure aware SOT of a point cloud is proposed. Specifically, the backbone network is combined with the auxiliary network to learn point-wise representations. During the training stage, the subsidiary network is used to perform additional tasks and supervisions, which guides the backbone network to extract discriminative structural features. During the inference stage, this network part is detached to meet a real-time requirement as well as to ensure the tracking accuracy. In addition, the impacts of the quantity setting of the input point cloud and re-initiation strategy are discussed; these are significant to the performance but have been ignored by former works. The experimental results show that the proposed method has a distinct improvement even if the tracked object is sparse and small scale.

中文翻译：

---

点云的结构感知 3D 单对象跟踪

点云的现有 3D 单对象跟踪器 (SOT) 在从点中提取特征时都应用了降尺度。这种操作会导致空间和结构信息的丢失，从而降低稀疏分布和小尺度对象的跟踪性能。为了解决这个问题，提出了一种点云的结构感知 SOT。具体来说，骨干网络与辅助网络相结合来学习逐点表示。在训练阶段，辅助网络用于执行附加任务和监督，指导骨干网络提取判别性结构特征。在推理阶段，该网络部分被分离以满足实时性要求并确保跟踪精度。此外，讨论了输入点云的数量设置和重新启动策略的影响；这些对表演很重要，但被以前的作品忽略了。实验结果表明，即使跟踪对象稀疏且规模较小，所提出的方法也有明显的改进。