EUVIMEDEUVIMED entdecken
Crossref

CompTrack: Information Bottleneck-Guided Low-Rank Dynamic Token Compression for Point Cloud Tracking

Sifan Zhou, Yichao Cao, Jiahao Nie, Yuqian Fu, Ziyu Zhao, Xiaobo Lu, Shuo Wang

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (16) · 13773-13781

DOI: 10.1609/aaai.v40i16.38385 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Sifan Zhou und 6 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

3D single object tracking (SOT) in LiDAR point clouds is a critical task in computer vision and autonomous driving. Despite great success having been achieved, the inherent sparsity of point clouds introduces a dual-redundancy challenge that limits existing trackers: (1) vast spatial redundancy from background noise impairs accuracy, and (2) informational redundancy within the foreground hinders efficiency. To tackle these issues, we propose CompTrack, a novel end-to-end framework that systematically eliminates both forms of redundancy in point clouds. First, CompTrack incorporates a Spatial Foreground Predictor (SFP) module to filter out irrelevant background noise based on information entropy, addressing spatial redundancy. Subsequently, its core is an Information Bottleneck-guided Dynamic Token Compression (IB-DTC) module that eliminates the informational redundancy within the foreground. Theoretically grounded in low-rank approximation, this module leverages an online SVD analysis to adaptively compress the redundant foreground into a compact and highly informative set of proxy tokens. Extensive experiments on KITTI, nuScenes and Waymo datasets demonstrate that CompTrack achieves top-performing tracking performance with superior efficiency, running at a real-time 90 FPS on a single RTX 3090 GPU.

Zitieren

APA

Zhou, S., Cao, Y., Nie, J., Fu, Y., Zhao, Z., Lu, X., & Wang, S. (2026). CompTrack: Information Bottleneck-Guided Low-Rank Dynamic Token Compression for Point Cloud Tracking. Proceedings of the AAAI Conference on Artificial Intelligence, 40(16), 13773-13781. https://doi.org/10.1609/aaai.v40i16.38385

Vancouver

Zhou S, Cao Y, Nie J, Fu Y, Zhao Z, Lu X, et al. CompTrack: Information Bottleneck-Guided Low-Rank Dynamic Token Compression for Point Cloud Tracking. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(16):13773-13781. doi:10.1609/aaai.v40i16.38385

BibTeX
@article{Zhou2026,
  author = {Zhou, Sifan and Cao, Yichao and Nie, Jiahao and Fu, Yuqian and Zhao, Ziyu and Lu, Xiaobo and Wang, Shuo},
  title = {CompTrack: Information Bottleneck-Guided Low-Rank Dynamic Token Compression for Point Cloud Tracking},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {16},
  pages = {13773--13781},
  doi = {10.1609/aaai.v40i16.38385}
}
Kostenlos starten →