SiamMo: Siamese Motion-Centric 3D Object Tracking

TL;DR

SiamMo is a simple, motion-centric 3D object tracking method that improves accuracy and robustness by decoupling feature extraction from temporal fusion and integrating multi-scale motion features, outperforming state-of-the-art methods.

Contribution

Introducing SiamMo, a novel Siamese motion-centric tracking approach with a multi-scale feature aggregation and size-aware encoding, enhancing 3D tracking performance and robustness.

Findings

Achieves 90.1% precision on KITTI benchmark

Surpasses state-of-the-art tracking methods

Operates at 108 FPS with high robustness

Abstract

Current 3D single object tracking methods primarily rely on the Siamese matching-based paradigm, which struggles with textureless and incomplete LiDAR point clouds. Conversely, the motion-centric paradigm avoids appearance matching, thus overcoming these issues. However, its complex multi-stage pipeline and the limited temporal modeling capability of a single-stream architecture constrain its potential. In this paper, we introduce SiamMo, a novel and simple Siamese motion-centric tracking approach. Unlike the traditional single-stream architecture, we employ Siamese feature extraction for motion-centric tracking. This decouples feature extraction from temporal fusion, significantly enhancing tracking performance. Additionally, we design a Spatio-Temporal Feature Aggregation module to integrate Siamese features at multiple scales, capturing motion information effectively. We also introduce a Box-aware Feature Encoding module to encode object size priors into motion estimation. SiamMo is a purely motion-centric tracker that eliminates the need for additional processes like segmentation and box refinement. Without whistles and bells, SiamMo not only surpasses state-of-the-art methods across multiple benchmarks but also demonstrates exceptional robustness in challenging scenarios. SiamMo sets a new record on the KITTI tracking benchmark with 90.1\% precision while maintaining a high inference speed of 108 FPS. The code will be released at https://github.com/HDU-VRLab/SiamMo.