<div align="center"> <h1>MapDistill <img src="assets/icon.png" width="30"></h1> <h3>Boosting Efficient Camera-based HD Map Construction via Camera-LiDAR Fusion Model Distillation</h3>

ArXiv Preprint (arXiv 2407.11682)

<center> <img src='assets/framework.png'> </center> </div>

Table of Contents

• News
• TODO List
• License
• Acknowledgements
• Citation

News

• Jul. 1st, 2024: :fire: MapDistill is accepted to ECCV 2024. Code/Models are coming soon. Please stay tuned! :coffee:

TODO List

• [x] Initial release. 🚀
• [ ] Getting Started.
• [ ] Installation.
• [ ] MapDistill checkpoints.
• [ ] MapDistill code.
• [ ] ...

License

This work is under the Apache License Version 2.0, while some specific operations in this codebase might be with other licenses. Please refer to LICENSE for a more careful check, if you are using our code for commercial matters.

Acknowledgements

MapDistill is based on MapTR and MapTRv2. It is also greatly inspired by the following outstanding contributions to the open-source community: mmdetection3d, BEVFormer, GKT, BEVDistill.

Citation

If you find MapDistill is useful in your research or applications, please consider giving us a star 🌟 and citing it by the following BibTeX entry.