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
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.
BibTeX
@inproceedings{ijcai2026_bevformertempora,
title = {BEVFormer++: Temporal Amplified BEVformer with Explicit Parameter Prediction for Automatic Trajectory Prediction},
author = {Jiabin Fang and Xu Zhang and Zhuoming Ding and Xuan Liu and Meifang Zhang and Jin Yuan and Yuyi Wang},
booktitle = {IJCAI 2026},
year = {2026}
}