提出一种端到端的3D点云目标追踪框架，兼顾精度与速度。
FocusTrack: One-Stage Focus-and-Suppress Framework for 3D Point Cloud Object Tracking
- 一阶段统一建模运动与语义，避免分步处理误差累积
- 在KITTI/nuScenes/Waymo上达到新最优性能，推理速度达105 FPS
- 适合需要高实时性与高精度的自动驾驶场景
在3D点云目标追踪中，基于运动的方法因在建模帧间运动方面表现优异而备受关注。然而，现有两阶段方法存在根本缺陷：(1) 由于先进行显式前景分割再估计运动，导致优化解耦引发误差累积；(2) 顺序处理造成计算瓶颈。为此，我们提出FocusTrack，一种新颖的一阶段追踪框架，通过两个核心创新实现运动-语义联合建模：帧间运动建模（IMM）和聚焦-抑制注意力机制。IMM模块采用时序差分孪生编码器，捕捉相邻帧间的全局运动模式。聚焦-抑制注意力机制则利用运动显著特征门控增强前景语义，并基于来自IMM的时序感知运动上下文抑制背景噪声，无需显式分割。基于上述设计，FocusTrack实现端到端训练与紧凑的一阶段流水线。在KITTI、nuScenes和Waymo等主流3D追踪基准上的大量实验表明，FocusTrack在保持高速运行（105 FPS）的同时达到新的最先进性能。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。