Efficient 3d object tracking without templates speeds up lidar data processing
TFTrack: A Template-Free Framework for Efficient 3D Point Cloud Tracking
Computer Vision and Pattern RecognitionArtificial Intelligence
Summary
Tracking moving objects in 3D using sensors like LiDAR usually needs complicated methods that compare past and current data side-by-side, which can be slow and resource-heavy. The authors show that keeping track just needs the last known position and simple geometric clues, without comparing to a separate template. They created a new method called TFTrack that works faster and uses less computing power while still being accurate. Their approach lets robots and self-driving cars track objects in real time more efficiently.
3D single object trackingLiDARpoint cloudSiamese trackingbounding boxgeometric alignmentmotion modelingreal-time processingrobotic perceptionKITTI benchmark
Authors
Zhaofeng Hu, Sifan Zhou, Jiahao Nie, Ziyu Zhao, Weizi Li, Ci-jyun Liang
Abstract
LiDAR-based 3D Single Object Tracking (3D SOT) is critical for robotic perception and navigation and aims to localize dynamic objects across frames in sparse point clouds. Existing methods, rooted in the Siamese tracking paradigm from 2D vision, rely on costly dual-input designs and excessive motion modeling guided by template priors, hindering their efficiency. Our in-depth analysis reveals: (i) the template paradigm is redundant, as the previous bounding box center encodes sufficient historical context; (ii) complex motion modeling is unnecessary, as geometric alignment provides adequate motion priors. Based on the above findings, we propose the first Template-Free Tracking framework (TFTrack). The novel framework eliminates the need for template-search pairings and operates directly on the current frame guided solely by the prior bounding box center and size. We instantiate this paradigm into three variants: TFTrack-Voxel, TFTrack-Pillar, and TFTrack-Point, to explore different 3D representations under a unified framework, ensuring flexibility across sparse and dense scenes. Extensive experiments on KITTI and nuScenes benchmarks show that TFTrack is competitive with leading template-based trackers, while reducing FLOPs by approximately 50% and running at approximately 120 FPS. By simplifying overcomplicated motion-centric designs, TFTrack establishes a new minimalist paradigm for efficient 3D point cloud tracking, paving the way for real-time and resource-efficient deployment in embedded robotic systems, such as autonomous vehicles. The code is available at https://github.com/tftrack-anonymous/TFTrack/tree/main.