Proceedings

BEVFormer++: Temporal Amplified BEVformer with Explicit Parameter Prediction for Automatic Trajectory Prediction

Jiabin Fang, Xu Zhang, Zhuoming Ding, Xuan Liu, Meifang Zhang, Jin Yuan, Yuyi Wang

Download BibTeX Cite

Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. Main Track. Pages 1079-1087.

https://doi.org/10.24963/ijcai.2026/121

Keywords

  • Computer Vision: Motion and tracking
  • Computer Vision: Action and behavior recognition
  • Computer Vision: Multimodal learning

Abstract

Vision-based trajectory prediction with BEV representations has achieved promising results, yet existing methods often suffer from limited temporal modeling and insufficient characterization of motion dynamics. To address these issues, we propose a temporally enhanced framework with explicit motion parameter prediction. Specifically, we introduce BEVFormer++, which leverages multi-view images and BEV features from multiple preceding timesteps to generate more robust BEV representations, along with BEV differential features to capture temporal variations. Moreover, we propose a motion-parameter-decoupled tracking module that explicitly estimates velocity, acceleration, and heading angle, providing informative motion cues for trajectory prediction. Extensive experimental results demonstrate that our method outperforms state-of-the-art approaches and can be seamlessly integrated into existing vision-based frameworks, consistently yielding performance improvements.

Jiabin Fang, Xu Zhang, Zhuoming Ding, Xuan Liu, Meifang Zhang, Jin Yuan, and Yuyi Wang. 2026. BEVFormer++: Temporal Amplified BEVformer with Explicit Parameter Prediction for Automatic Trajectory Prediction. In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26. IJCAI, 1079–1087. https://doi.org/10.24963/ijcai.2026/121
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards