EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

BEVPredFormer: Spatio-Temporal Attention for BEV Instance Prediction in Autonomous Driving

Miguel Antunes-García, Santiago Montiel-Marín, Fabio Sánchez-García, Rodrigo Gutiérrez-Moreno, Rafael Barea, Luis M. Bergasa

Sensors · 14.11.2026 · 26 (22) · 7206

DOI: 10.3390/s26227206 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 14.11.2026. Verfasst von Miguel Antunes-García und 5 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministerio de Ciencia, Innovación y Universidades, Comunidad de Madrid.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

A robust awareness of how dynamic scenes evolve is essential for Autonomous Driving systems, as they must accurately detect, track, and predict the behaviour of surrounding obstacles. Traditional perception pipelines that rely on modular architectures tend to suffer from cumulative errors and latency. Instance Prediction models provide a unified solution, performing Bird’s-Eye-View segmentation and motion estimation across current and future frames using information directly obtained from different sensors. However, a key challenge in these models lies in the effective processing of the dense spatial and temporal information inherent in dynamic driving environments. This level of complexity demands architectures capable of capturing fine-grained motion patterns and long-range dependencies. We introduce BEVPredFormer, a novel multi-camera architecture for Bird’s-Eye-View Instance Prediction that uses attention-based temporal processing to improve temporal and spatial comprehension of the scene and relies on an attention-based 3D projection of the camera information. BEVPredFormer employs a recurrent-free design that incorporates gated transformer layers, divided spatio-temporal attention mechanisms, and multi-scale prediction heads. Additionally, we incorporate a difference-guided feature extraction module that enhances temporal representations. Extensive ablation studies validate the design of the temporal module, including the configuration of the spatio-temporal attention blocks and the difference module, as well as the choice of feature extractor and view transform, the training strategy and the input resolution. When evaluated on the nuScenes dataset, BEVPredFormer performs on par with or surpasses state-of-the-art methods, particularly in long-range scenarios, at a moderate computational cost.

Förderung

  • Ministerio de Ciencia, Innovación y Universidades
  • Comunidad de Madrid

Zitieren

APA

Antunes-García, M., Montiel-Marín, S., Sánchez-García, F., Gutiérrez-Moreno, R., Barea, R., & Bergasa, L. M. (2026). BEVPredFormer: Spatio-Temporal Attention for BEV Instance Prediction in Autonomous Driving. Sensors, 26(22), 7206. https://doi.org/10.3390/s26227206

Vancouver

Antunes-García M, Montiel-Marín S, Sánchez-García F, Gutiérrez-Moreno R, Barea R, Bergasa LM. BEVPredFormer: Spatio-Temporal Attention for BEV Instance Prediction in Autonomous Driving. Sensors. 2026;26(22):7206. doi:10.3390/s26227206

BibTeX
@article{AntunesGarca2026,
  author = {Antunes-García, Miguel and Montiel-Marín, Santiago and Sánchez-García, Fabio and Gutiérrez-Moreno, Rodrigo and Barea, Rafael and Bergasa, Luis M.},
  title = {BEVPredFormer: Spatio-Temporal Attention for BEV Instance Prediction in Autonomous Driving},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {22},
  pages = {7206},
  doi = {10.3390/s26227206}
}
Kostenlos starten →