Awesome

BEVerse

The official implementation of the paper BEVerse: Unified Perception and Prediction in Birds-Eye-View for Vision-Centric Autonomous Driving.

News

2022.07.20: We release the code and models of BEVerse.

Model Zoo

Method	mAP	NDS	IoU (Map)	IoU (Motion)	VPQ	Model
BEVerse-Tiny	32.1	46.6	48.7	38.7	33.3	Google Drive
BEVerse-Small	35.2	49.5	51.7	40.9	36.1	Google Drive

Installation

Please check installation for installation and data_preparation for preparing the nuScenes dataset.

Getting Started

Please check getting_started for training, evaluation, and visualization of BEVerse.

Visualization

visualization

Acknowledgement

This project is mainly based on the following open-sourced projects: open-mmlab, BEVDet, HDMapNet, Fiery.

Bibtex

If this work is helpful for your research, please consider citing the following BibTeX entry.

@article{zhang2022beverse,
  title={BEVerse: Unified Perception and Prediction in Birds-Eye-View for Vision-Centric Autonomous Driving},
  author={Zhang, Yunpeng and Zhu, Zheng and Zheng, Wenzhao and Huang, Junjie and Huang, Guan and Zhou, Jie and Lu, Jiwen},
  journal={arXiv preprint arXiv:2205.09743},
  year={2022}
}

@article{huang2021bevdet,
  title={BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-View},
  author={Huang, Junjie and Huang, Guan and Zhu, Zheng and Yun, Ye and Du, Dalong},
  journal={arXiv preprint arXiv:2112.11790},
  year={2021}
}