MLVSNet: Multi-Level Voting Siamese Network for 3D Visual Tracking

Zhoutao Wang, Qian Xie, Yu-Kun Lai, Jing Wu, Kun Long, Jun Wang; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021, pp. 3101-3110

Abstract


Benefiting from the excellent performance of Siamese-based trackers, huge progress on 2D visual tracking has been achieved. However, 3D visual tracking is still under-explored. Inspired by the idea of Hough voting in 3D object detection, in this paper, we propose a Multi-level Voting Siamese Network (MLVSNet) for 3D visual tracking from outdoor point cloud sequences. To deal with sparsity in outdoor 3D point clouds, we propose to perform Hough voting on multi-level features to get more vote centers and retain more useful information, instead of voting only on the final level feature as in previous methods. We also design an efficient and lightweight Target-Guided Attention (TGA) module to transfer the target information and highlight the target points in the search area. Moreover, we propose a Vote-cluster Feature Enhancement (VFE) module to exploit the relationships between different vote clusters. Extensive experiments on the 3D tracking benchmark of KITTI dataset demonstrate that our MLVSNet outperforms state-of-the-art methods with significant margins. Code will be available at https://github.com/CodeWZT/MLVSNet.

Related Material


[pdf]
[bibtex]
@InProceedings{Wang_2021_ICCV, author = {Wang, Zhoutao and Xie, Qian and Lai, Yu-Kun and Wu, Jing and Long, Kun and Wang, Jun}, title = {MLVSNet: Multi-Level Voting Siamese Network for 3D Visual Tracking}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2021}, pages = {3101-3110} }