EUVIMEDEUVIMED entdecken
Crossref

BEVMamba: Time Sequence Dense Bird’s-Eye-View Perception Modeling With State Space Model

Xiao Liu, Jiaru Zhong, Chao Sun

IEEE Transactions on Intelligent Transportation Systems · 2025-09 · 26 (9) · 13466-13476

DOI: 10.1109/tits.2025.3569706 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Intelligent Transportation Systems, 2025-09. Verfasst von Xiao Liu und 2 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 86 Literaturangaben. Gefördert von: Key-Area Research and Development Program of Guangdong Province, Shenzhen Science and Technology Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BEV-based 3D perception with multi-frame images input is crucial for autonomous driving. However, current methods for temporal BEV perception fail to fully utilize long sequence features because of local fusion or high complexity. Recently, Mamba, a powerful temporal modeling network with linear complexity, has shown exceptional performance in various 2D vision tasks, but its application to 3D perception tasks remains unexplored. Therefore, this paper proposes a general BEV perception backbone named BEVMamba, which is the first work to leverage State Space Model for 3D perception. Built upon the BEVFormer, to adapt Mamba for 3D perception we first add Hybrid Positional Encoding to the BEV features, enabling the networks to be aware of their spatial-temporal position. In the Temporal SSM block, the proposed 3D Factorized Scan ensures that historical BEV features are enriched with global temporal-spatial information. Subsequently, the Spatial-Temporal Corridor Fusion aggregates all BEV features in a physically meaningful manner, achieving precise feature fusion. The reliable BEV features obtained by BEVMamba are used for various perception tasks, including 3D object detection and 3D occupancy prediction. Results on the nuScenes and Occ-3D nuScenes datasets show that BEVMamba outperforms its baseline BEVFormer in both dense and sparse perception tasks and demonstrates competitive performance compared to other methods, highlighting the potential of Mamba in 3D perception tasks. The code will be available at https://github.com/Liuxiaoaaa/bevmamba

Förderung

  • Key-Area Research and Development Program of Guangdong Province
  • Shenzhen Science and Technology Program

Zitieren

APA

Liu, X., Zhong, J., & Sun, C. (2025). BEVMamba: Time Sequence Dense Bird’s-Eye-View Perception Modeling With State Space Model. IEEE Transactions on Intelligent Transportation Systems, 26(9), 13466-13476. https://doi.org/10.1109/tits.2025.3569706

Vancouver

Liu X, Zhong J, Sun C. BEVMamba: Time Sequence Dense Bird’s-Eye-View Perception Modeling With State Space Model. IEEE Transactions on Intelligent Transportation Systems. 2025;26(9):13466-13476. doi:10.1109/tits.2025.3569706

BibTeX
@article{Liu2025,
  author = {Liu, Xiao and Zhong, Jiaru and Sun, Chao},
  title = {BEVMamba: Time Sequence Dense Bird’s-Eye-View Perception Modeling With State Space Model},
  journal = {IEEE Transactions on Intelligent Transportation Systems},
  year = {2025},
  volume = {26},
  number = {9},
  pages = {13466--13476},
  doi = {10.1109/tits.2025.3569706}
}
Kostenlos starten →