Beyond 3D Siamese Tracking: A Motion-Centric Paradigm for 3D Single Object Tracking in Point Clouds
This addresses a critical bottleneck in autonomous driving by improving tracking accuracy for textureless and incomplete point clouds, though it is an incremental advancement over existing paradigms.
The paper tackles the problem of 3D single object tracking in LiDAR point clouds by moving beyond appearance-based Siamese methods to a motion-centric paradigm, resulting in significant performance gains of ~8%, ~17%, and ~22% on three datasets while running at 57FPS.
3D single object tracking (3D SOT) in LiDAR point clouds plays a crucial role in autonomous driving. Current approaches all follow the Siamese paradigm based on appearance matching. However, LiDAR point clouds are usually textureless and incomplete, which hinders effective appearance matching. Besides, previous methods greatly overlook the critical motion clues among targets. In this work, beyond 3D Siamese tracking, we introduce a motion-centric paradigm to handle 3D SOT from a new perspective. Following this paradigm, we propose a matching-free two-stage tracker M^2-Track. At the 1^st-stage, M^2-Track localizes the target within successive frames via motion transformation. Then it refines the target box through motion-assisted shape completion at the 2^nd-stage. Extensive experiments confirm that M^2-Track significantly outperforms previous state-of-the-arts on three large-scale datasets while running at 57FPS (~8%, ~17%, and ~22%) precision gains on KITTI, NuScenes, and Waymo Open Dataset respectively). Further analysis verifies each component's effectiveness and shows the motion-centric paradigm's promising potential when combined with appearance matching.