GLT-T: Global-Local Transformer Voting for 3D Single Object Tracking in Point Clouds

TL;DR

This paper introduces GLT-T, a novel 3D object tracking method that employs a global-local transformer voting scheme to generate high-quality proposals by enhancing seed point features and importance weighting, achieving state-of-the-art results.

Contribution

The paper proposes a global-local transformer module and an importance prediction strategy to improve seed point feature representation and voting in 3D object tracking.

Findings

Achieves state-of-the-art performance on KITTI and NuScenes benchmarks.

Demonstrates the effectiveness of the global-local transformer voting scheme.

Shows improved proposal quality over VoteNet through ablation studies.

Abstract

Current 3D single object tracking methods are typically based on VoteNet, a 3D region proposal network. Despite the success, using a single seed point feature as the cue for offset learning in VoteNet prevents high-quality 3D proposals from being generated. Moreover, seed points with different importance are treated equally in the voting process, aggravating this defect. To address these issues, we propose a novel global-local transformer voting scheme to provide more informative cues and guide the model pay more attention on potential seed points, promoting the generation of high-quality 3D proposals. Technically, a global-local transformer (GLT) module is employed to integrate object- and patch-aware prior into seed point features to effectively form strong feature representation for geometric positions of the seed points, thus providing more robust and accurate cues for offset learning. Subsequently, a simple yet effective training strategy is designed to train the GLT module. We develop an importance prediction branch to learn the potential importance of the seed points and treat the output weights vector as a training constraint term. By incorporating the above components together, we exhibit a superior tracking method GLT-T. Extensive experiments on challenging KITTI and NuScenes benchmarks demonstrate that GLT-T achieves state-of-the-art performance in the 3D single object tracking task. Besides, further ablation studies show the advantages of the proposed global-local transformer voting scheme over the original VoteNet. Code and models will be available at https://github.com/haooozi/GLT-T.