HeightAware-BEV: Height-Aware Feature Mapping for Efficient Bird's-Eye-View Perception
Renjie Zhou, Jiachen Li, Zhen Su, Chao Lu, Zhengjun Wang
Abstract
Bird’s-Eye View (BEV) perception has gained significant attention in autonomous driving and robotics due to its advantages in simplifying modality alignment and feature fusion. Addressing the challenge of jointly optimizing performance and efficiency in 2D-3D view transformation, we identify that, compared to depth information which is viewpoint-dependent and requires camera intrinsics for estimation, height information can maintains prediction consistency across different camera perspectives. Based on this insight, we propose the HeightAware-BEV framework, which achieves efficient and accurate view transformation through height-aware feature mapping. (1) Building on an efficient projection-based view transformation approach, 3D voxels directly query the height probability distribution predicted by images according to grid height, weighting corresponding features to enable precise and efficient feature projection; (2) Design a dynamic feature filtering mechanism to filter out task-irrelevant features during the view transformation process. Additionally, a weakly-supervised training strategy is designed to improve model performance in scenarios with limited samples. The HeightAware-BEV (R50@448×800) achieves an IOU of 47.8% on the nuScenes validation set and 60 FPS on 2080Ti, outperforming advanced methods such as SimpleBEV and PointBEV. The code is available at https://github.com/Zhou-Renjie/HeightAware-BEV.
BibTeX
@inproceedings{iros2025_heightawarebevhe,
title = {HeightAware-BEV: Height-Aware Feature Mapping for Efficient Bird's-Eye-View Perception},
author = {Renjie Zhou and Jiachen Li and Zhen Su and Chao Lu and Zhengjun Wang},
booktitle = {IROS 2025},
year = {2025}
}