Home

Awesome

Temporal Enhanced Training of Multi-view 3D Object Detector via Historical Object Prediction

PWC

This repo is the official implementation of "Temporal Enhanced Training of Multi-view 3D Object Detector via Historical Object Prediction" by Zhuofan Zong, Dongzhi Jiang, Guanglu Song, Zeyue Xue, Jingyong Su, Hongsheng Li, and Yu Liu.

News

Model Zoo

Result on BEVDet4D-Depth

modelbackbonepretrainimg sizeEpochNDSmAPconfigckptlog
BEVDet4D-Depth(Baseline)Res50ImageNet256x704240.49300.3848cfgckptlog
HoP_BEVDet4D-DepthRes50ImageNet256x704240.50990.3990cfgckptlog

Get Started

Install

We train our models under the following environment:

python=3.6.9
pytorch=1.8.1
torchvision=0.9.1
cuda=11.2

Other versions may possibly be imcompatible.

We use MMDetection3D V1.0.0rc4, MMDetection V2.24.0 and MMCV V1.5.0. The source code of MMDetection3D has been included in this repo.

You can take the following steps to install packages above:

  1. Build MMCV following official instructions.

  2. Install MMDetection by

    pip install mmdet==2.24.0
    
  3. Copy HoP repo and install MMDetection3D.

    git clone git@github.com:Sense-X/HoP.git
    cd HoP
    pip install -e .
    

Data Preparation

Follow the steps to prepare nuScenes Dataset introduced in nuscenes_det.md and create the pkl by running:

python tools/create_data_bevdet.py

Train HoP

# single gpu
python tools/train.py configs/hop_bevdet/hop_bevdet4d-r50-depth.py
# multiple gpu
./tools/dist_train.sh configs/hop_bevdet/hop_bevdet4d-r50-depth.py $num_gpu

Eval HoP

# single gpu
python tools/test.py configs/hop_bevdet/hop_bevdet4d-r50-depth.py $checkpoint --eval bbox
# multiple gpu
./tools/dist_test.sh configs/hop_bevdet/hop_bevdet4d-r50-depth.py $checkpoint $num_gpu --eval bbox

Method

<img src="resources/HoP_framework.png" width="1000" >

TODO

Cite HoP

If you find this repository useful, please use the following BibTeX entry for citation.

@misc{hop2023,
      title={Temporal Enhanced Training of Multi-view 3D Object Detector via Historical Object Prediction},
      author={Zhuofan Zong and Dongzhi Jiang and Guanglu Song and Zeyue Xue and Jingyong Su and Hongsheng Li and Yu Liu},
      year={2023},
      eprint={2304.00967},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

License

This project is released under the MIT license. Please see the LICENSE file for more information.