BEVDepth is a new 3D object detector with a trustworthy depth estimation. For more details, please refer to our paper on Arxiv.
- 【2022/06/21】 We have released our paper on Arxiv.
Step 0. Install pytorch(v1.9.0).
Step 1. Install MMDetection3D(v0.18.0).
Step 2. Install requirements.
pip install -r requirements.txt
Step 3. Install BEVDepth(gpu required).
python setup.py develop
Step 0. Download nuScenes official dataset.
Step 1. Symlink the dataset root to ./data/
.
ln -s [nuscenes root] ./data/
The directory will be as follows.
BEVDepth
├── data
│ ├── nuScenes
│ │ ├── maps
│ │ ├── samples
│ │ ├── sweeps
│ │ ├── v1.0-test
| | ├── v1.0-trainval
Step 2. Prepare infos.
python scripts/gen_info.py
Step 3. Prepare depth gt.
python scripts/gen_depth_gt.py
Train.
python [EXP_PATH] --amp_backend native -b 8 --gpus 8
Eval.
python [EXP_PATH] --ckpt_path [CKPT_PATH] -e -b 8 --gpus 8
Backbone | mAP | mATE | mASE | mAOE | mAVE | mAAE | NDS | weights |
---|---|---|---|---|---|---|---|---|
R50 | 0.3329 | 0.6832 | 0.2761 | 0.5446 | 0.5258 | 0.2259 | 0.4409 | github |
If you use BEVDepth in your research, please cite our work by using the following BibTeX entry:
@article{li2022bevdepth,
title={BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detection},
author={Li, Yinhao and Ge, Zheng and Yu, Guanyi and Yang, Jinrong and Wang, Zengran and Shi, Yukang and Sun, Jianjian and Li, Zeming},
journal={arXiv preprint arXiv:2206.10092},
year={2022}
}