AerialFusionMapNet

Online HD Map Construction with Aerial-Onboard BEV Fusion

arXiv Paper GitHub

Introduction

This repository provides pretrained checkpoints for “AerialFusionMapNet: Online HD Map Construction with Aerial-Onboard BEV Fusion”, accepted at IEEE ITSC 2026.

AerialFusionMapNet extends online HD map construction by fusing camera-based BEV features with ego-aligned aerial imagery from AID4AD. The released checkpoints are intended to reproduce the reported evaluation results and support further research on aerial-ground fusion for online map construction.

For implementation details, configuration files, and evaluation instructions, please refer to the GitHub repository.

Citation

If you use AerialFusionMapNet in your research, please cite:

@article{lengerer2026aerialfusionmapnet,
  title={AerialFusionMapNet: Online HD Map Construction with Aerial-Onboard BEV Fusion},
  author={Daniel Lengerer and Mathias Pechinger and Klaus Bogenberger and Carsten Markgraf},
  year={2026},
  journal={arXiv preprint arXiv:2606.24784}
}
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Paper for dlengerer/AerialFusionMapNet