EUVIMEDEUVIMED entdecken
Crossref

BEVFormer: Learning Bird’s-Eye-View Representation From LiDAR-Camera via Spatiotemporal Transformers

Zhiqi Li, Wenhai Wang, Hongyang Li, Enze Xie, Chonghao Sima, Tong Lu, Qiao Yu, Jifeng Dai

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2025-03 · 47 (3) · 2020-2036

DOI: 10.1109/tpami.2024.3515454 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025-03. Verfasst von Zhiqi Li und 7 weiteren Autor:innen. Die Arbeit wurde bisher 356-mal zitiert (Crossref) und nennt 90 Literaturangaben. Gefördert von: National Key R&D Program of China, National Natural Science Foundation of China, National Key R&D Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multi-modality fusion strategy is currently the de-facto most competitive solution for 3D perception tasks. In this work, we present a new framework termed BEVFormer, which learns unified BEV representations from multi-modality data with spatiotemporal transformers to support multiple autonomous driving perception tasks. In a nutshell, BEVFormer exploits both spatial and temporal information by interacting with spatial and temporal space through predefined grid-shaped BEV queries. To aggregate spatial information, we design spatial cross-attention that each BEV query extracts the spatial features from both point cloud and camera input, thus completing multi-modality information fusion under BEV space. For temporal information, we propose temporal self-attention to fuse the history BEV information recurrently. By comparing with other fusion paradigms, we demonstrate that the fusion method proposed in this work is both succinct and effective. Our approach achieves the new state-of-the-art 74.1% in terms of NDS metric on the nuScenes test set. In addition, we extend BEVFormer to encompass a wide range of autonomous driving tasks, including object tracking, vectorized mapping, occupancy prediction, and end-to-end autonomous driving, achieving outstanding results across these tasks. The code is released at https://github.com/fundamentalvision/BEVFormer.

Förderung

  • National Key R&D Program of China
  • National Natural Science Foundation of China
  • National Key R&D Project
  • Oriental Leading Talent Project
  • China Mobile Zijin Innovation Institute

Zitieren

APA

Li, Z., Wang, W., Li, H., Xie, E., Sima, C., Lu, T., Yu, Q., & Dai, J. (2025). BEVFormer: Learning Bird’s-Eye-View Representation From LiDAR-Camera via Spatiotemporal Transformers. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(3), 2020-2036. https://doi.org/10.1109/tpami.2024.3515454

Vancouver

Li Z, Wang W, Li H, Xie E, Sima C, Lu T, et al. BEVFormer: Learning Bird’s-Eye-View Representation From LiDAR-Camera via Spatiotemporal Transformers. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2025;47(3):2020-2036. doi:10.1109/tpami.2024.3515454

BibTeX
@article{Li2025,
  author = {Li, Zhiqi and Wang, Wenhai and Li, Hongyang and Xie, Enze and Sima, Chonghao and Lu, Tong and Yu, Qiao and Dai, Jifeng},
  title = {BEVFormer: Learning Bird’s-Eye-View Representation From LiDAR-Camera via Spatiotemporal Transformers},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2025},
  volume = {47},
  number = {3},
  pages = {2020--2036},
  doi = {10.1109/tpami.2024.3515454}
}
Kostenlos starten →