CodeWZT / MLVSNet

[ICCV 2021] PyTorch code for “MLVSNet: Multi-level Voting Siamese Network for 3D Visual Tracking”

[ICCV 2021] PyTorch code for “MLVSNet: Multi-level Voting Siamese Network for 3D Visual Tracking”.

Introduction

This repository is released for MLVSNet in our ICCV 2021 paper. Here we include our MLVSNet model (PyTorch) and code for data preparation, training and testing on KITTI tracking dataset.

Preliminary

• Install python 3.6.

• Install dependencies.

    pip install -r requirements.txt

• Build _ext module.

    python setup.py build_ext --inplace

• Download the dataset from KITTI Tracking.

  Download velodyne, calib and label_02 in the dataset and place them under the same parent folder.

Evaluation

Train a new MLVSNet on KITTI data:

python train_tracking.py --data_dir=<kitti data path>

Test a new MLVSNet model on KITTI data:

python test_tracking.py --data_dir=<kitti data path>

Please refer to the code for setting of other optional arguments, including data split, training and testing parameters, etc.

Acknowledgements

This code largely benefits from excellent works P2B, please also consider cite P2B if you use this code. They help and inspire this work.

Citation

@InProceedings{Wang_2021_ICCV,
    author    = {Wang, Zhoutao and Xie, Qian and Lai, Yu-Kun and Wu, Jing and Long, Kun and Wang, Jun},
    title     = {MLVSNet: Multi-Level Voting Siamese Network for 3D Visual Tracking},
    booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
    month     = {October},
    year      = {2021},
    pages     = {3101-3110}
}