Abstract
In 3D point cloud object tracking, the motion-centric methods have emerged as a promising avenue due to its superior performance in modeling inter-frame motion. However, existing two-stage motion-based approaches suffer from fundamental limitations: (1) error accumulation due to decoupled optimization caused by explicit foreground segmentation prior to motion estimation, and (2) computational bottlenecks from sequential processing. To address these challenges, we propose FocusTrack, a novel one-stage paradigms tracking framework that unifies motion-semantics co-modeling through two core innovations: Inter-frame Motion Modeling (IMM) and Focus-and-Suppress Attention. The IMM module employs a temp-oral-difference siamese encoder to capture global motion patterns between adjacent frames. The Focus-and-Suppress attention that enhance the foreground semantics via motion-salient feature gating and suppress the background noise based on the temporal-aware motion context from IMM without explicit segmentation. Based on above two designs, FocusTrack enables end-to-end training with compact one-stage pipeline. Extensive experiments on prominent 3D tracking benchmarks, such as KITTI, nuScenes, and Waymo, demonstrate that the FocusTrack achieves new SOTA performance while running at a high speed with 105 FPS.
Abstract (translated)
在三维点云物体跟踪领域，以运动为中心的方法由于其在建模帧间运动方面的优越性能而成为一条有前途的途径。然而，现有的两阶段基于运动的方法存在根本性的局限性：(1) 因为在运动估计之前进行显式的前景分割而导致解耦优化所造成的误差积累；(2) 由顺序处理导致的计算瓶颈。为了应对这些挑战，我们提出了FocusTrack——一种新颖的一阶段跟踪框架，通过两个核心创新将运动-语义共模建整合在一起：帧间运动建模（IMM）和关注与抑制注意力机制。 IMM模块采用时序差异暹罗编码器来捕捉相邻帧之间的全局运动模式。关注与抑制注意机制则通过对来自IMM的时序感知运动上下文进行基于运动显著性特征门控的方法，增强前景语义并压制背景噪声，而无需显式分割。 根据以上两种设计，FocusTrack能够实现端到端训练，并且具有紧凑的一阶段流水线。在诸如KITTI、nuScenes和Waymo等突出的3D跟踪基准测试中进行广泛的实验表明，FocusTrack能够在以每秒105帧的速度运行的同时达到新的SOTA（State-of-the-Art）性能水平。
URL
https://arxiv.org/abs/2602.24133
