Mapping like a Skeptic: Probabilistic BEV Projection for Online HD Mapping


Fatih Erdoğan (Koç University), Merve Rabia Barin (Koç University), Fatma Güney (Koç University)
The 35th British Machine Vision Conference

Abstract

Constructing high-definition (HD) maps from sensory input requires accurately map- ping the road elements in image space to the Bird’s Eye View (BEV) space. The pre- cision of this mapping directly impacts the quality of the final vectorized HD map. Existing HD mapping approaches outsource the projection to standard mapping tech- niques, such as attention-based ones. However, these methods struggle with accuracy due to generalization problems, often hallucinating non-existent road elements. Our key idea is to start with a geometric mapping based on camera parameters and adapt it to the scene to extract relevant map information from camera images. To implement this, we propose a novel probabilistic projection mechanism with confidence scores to (i) refine the mapping to better align with the scene and (ii) filter out irrelevant ele- ments that should not influence HD map generation. In addition, we improve tempo- ral processing by using confidence scores to selectively accumulate reliable informa- tion over time. Experiments on new splits of the nuScenes and Argoverse2 datasets demonstrate improved performance over state-of-the-art approaches, indicating better generalization. The improvements are particularly pronounced on nuScenes and in the challenging long perception range. Our code and model checkpoints are available at https://github.com/Fatih-Erdogan/mapping-like-skeptic.

Citation

@inproceedings{Erdoğan_2025_BMVC,
author    = {Fatih Erdoğan and Merve Rabia Barin and Fatma Güney},
title     = {Mapping like a Skeptic: Probabilistic BEV Projection for Online HD Mapping},
booktitle = {36th British Machine Vision Conference 2025, {BMVC} 2025, Sheffield, UK, November 24-27, 2025},
publisher = {BMVA},
year      = {2025},
url       = {https://bmva-archive.org.uk/bmvc/2025/assets/papers/Paper_745/paper.pdf}
}


Copyright © 2025 The British Machine Vision Association and Society for Pattern Recognition
The British Machine Vision Conference is organised by The British Machine Vision Association and Society for Pattern Recognition. The Association is a Company limited by guarantee, No.2543446, and a non-profit-making body, registered in England and Wales as Charity No.1002307 (Registered Office: Dept. of Computer Science, Durham University, South Road, Durham, DH1 3LE, UK).

Imprint | Data Protection