Awesome

BEVFormer: a Cutting-edge Baseline for Camera-based Detection

</div>

https://user-images.githubusercontent.com/27915819/161392594-fc0082f7-5c37-4919-830a-2dd423c1d025.mp4

BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers, ECCV 2022

Paper in arXiv | Paper in Chinese | OpenDriveLab

Slides in English | Occupancy and BEV Perception Talk Slides

Blog in Chinese | Video Talk and Slides (in Chinese)

BEV Perception Survey (Accepted by PAMI) | Github repo

News

[2022/6/16]: We added two BEVformer configurations, which require less GPU memory than the base version. Please pull this repo to obtain the latest codes.
[2022/6/13]: We release an initial version of BEVFormer. It achieves a baseline result of 51.7% NDS on nuScenes.
[2022/5/23]: 🚀🚀Built on top of BEVFormer, BEVFormer++, gathering up all best practices in recent SOTAs and our unique modification, ranks 1st on Waymo Open Datast 3D Camera-Only Detection Challenge. We will present BEVFormer++ on CVPR 2022 Autonomous Driving Workshop.
[2022/3/10]: 🚀BEVFormer achieve the SOTA on nuScenes Detection Task with 56.9% NDS (camera-only)! </br>

Abstract

In this work, the authors present a new framework termed BEVFormer, which learns unified BEV representations with spatiotemporal transformers to support multiple autonomous driving perception tasks. In a nutshell, BEVFormer exploits both spatial and temporal information by interacting with spatial and temporal space through predefined grid-shaped BEV queries. To aggregate spatial information, the authors design a spatial cross-attention that each BEV query extracts the spatial features from the regions of interest across camera views. For temporal information, the authors propose a temporal self-attention to recurrently fuse the history BEV information. The proposed approach achieves the new state-of-the-art 56.9% in terms of NDS metric on the nuScenes test set, which is 9.0 points higher than previous best arts and on par with the performance of LiDAR-based baselines.

Methods

method

Getting Started

Model Zoo

Backbone	Method	Lr Schd	NDS	mAP	memroy	Config	Download
R50	BEVFormer-tiny_fp16	24ep	35.9	25.7	-	config	model/log
R50	BEVFormer-tiny	24ep	35.4	25.2	6500M	config	model/log
R101-DCN	BEVFormer-small	24ep	47.9	37.0	10500M	config	model/log
R101-DCN	BEVFormer-base	24ep	51.7	41.6	28500M	config	model/log
R50	BEVformerV2-t1-base	24ep	42.6	35.1	23952M	config	model/log
R50	BEVformerV2-t1-base	48ep	43.9	35.9	23952M	config	model/log
R50	BEVformerV2-t1	24ep	45.3	38.1	37579M	config	model/log
R50	BEVformerV2-t1	48ep	46.5	39.5	37579M	config	model/log
R50	BEVformerV2-t2	24ep	51.8	42.0	38954M	config	model/log
R50	BEVformerV2-t2	48ep	52.6	43.1	38954M	config	model/log
R50	BEVformerV2-t8	24ep	55.3	46.0	40392M	config	model/log

The Baidu Driver Link for (BEVFormerV2 model and log)[https://pan.baidu.com/s/1ynzlAt1DQbH8NkqmisatTw?pwd=fdcv] is here.

Catalog

Bibtex

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

@article{li2022bevformer,
  title={BEVFormer: Learning Bird’s-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers},
  author={Li, Zhiqi and Wang, Wenhai and Li, Hongyang and Xie, Enze and Sima, Chonghao and Lu, Tong and Qiao, Yu and Dai, Jifeng}
  journal={arXiv preprint arXiv:2203.17270},
  year={2022}
}
@article{Yang2022BEVFormerVA,
  title={BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervision},
  author={Chenyu Yang and Yuntao Chen and Haofei Tian and Chenxin Tao and Xizhou Zhu and Zhaoxiang Zhang and Gao Huang and Hongyang Li and Y. Qiao and Lewei Lu and Jie Zhou and Jifeng Dai},
  journal={ArXiv},
  year={2022},
}

Acknowledgement

Many thanks to these excellent open source projects: