3D Single Object Tracking (SOT) is a fundamental task of computer vision, proving essential for applications like autonomous driving. It remains challenging to localize the target from surroundings due to appearance variations, distractors, and the high sparsity of point clouds. The spatial information indicating objects' spatial adjacency across consecutive frames is crucial for effective object tracking. However, existing trackers typically employ point-wise representation with irregular formats, leading to insufficient use of this important spatial knowledge. As a result, these trackers usually require elaborate designs and solving multiple subtasks. In this paper, we propose BEVTrack, a simple yet effective baseline that performs tracking in Bird's-Eye View (BEV). This representation greatly retains spatial information owing to its ordered structure and inherently encodes the implicit motion relations of the target as well as distractors. To achieve accurate regression for targets with diverse attributes (\textit{e.g.}, sizes and motion patterns), BEVTrack constructs the likelihood function with the learned underlying distributions adapted to different targets, rather than making a fixed Laplace or Gaussian assumption as in previous works. This provides valuable priors for tracking and thus further boosts performance. While only using a single regression loss with a plain convolutional architecture, BEVTrack achieves state-of-the-art performance on three large-scale datasets, KITTI, NuScenes, and Waymo Open Dataset while maintaining a high inference speed of about 200 FPS. The code will be released at https://github.com/xmm-prio/BEVTrack.

翻译：3D单目标跟踪是计算机视觉的基础任务，对自动驾驶等应用至关重要。由于外观变化、干扰物以及点云高度稀疏性，从环境中定位目标仍具挑战性。连续帧间反映目标空间邻接关系的空间信息对有效目标跟踪至关重要。然而，现有跟踪器通常采用不规则格式的点级表示，导致这一重要空间知识未被充分利用。因此，这些跟踪器通常需要精心设计并解决多个子任务。本文提出BEVTrack——一种在鸟瞰视角下进行跟踪的简单而有效的基线方法。该表示因其有序结构极大地保留了空间信息，并天然编码了目标及干扰物的隐式运动关系。为实现对具有不同属性（如尺寸和运动模式）目标的精确回归，BEVTrack通过学习适合不同目标的潜在分布来构建似然函数，而非像先前工作那样采用固定的拉普拉斯分布或高斯分布假设。这为跟踪提供了有价值的先验知识，进一步提升了性能。尽管仅使用单一回归损失和普通卷积架构，BEVTrack在KITTI、NuScenes和Waymo开放数据集三个大规模数据集上取得了最先进性能，同时保持约200 FPS的高推理速度。代码将发布在https://github.com/xmm-prio/BEVTrack。