Home

Awesome

<div align="center"> <h1>MV-JAR: Masked Voxel Jigsaw and Reconstruction for LiDAR-Based Self-Supervised Pre-Training</h1> <div> <a href='https://scholar.google.com/citations?user=MOobrCcAAAAJ&hl=zh-CN&authuser=1' target='_blank'>Runsen Xu</a>&emsp; <a href='https://tai-wang.github.io/' target='_blank'>Tai Wang</a>&emsp; <a href='http://zhangwenwei.cn/' target='_blank'>Wenwei Zhang</a>&emsp; <a href='https://www.rjchen.site/' target='_blank'>Runjian Chen</a>&emsp; <a href='http://www.jinkuncao.com/' target='_blank'>Jinkun Cao</a>&emsp; <a href='https://oceanpang.github.io/' target='_blank'>Jiangmiao Pang*</a>&emsp; <a href='http://dahua.site/' target='_blank'>Dahua Lin</a>&emsp; </div> <a href='https://cvpr2023.thecvf.com/' target='_blank'>CVPR 2023</a>

<a href='https://arxiv.org/abs/2303.13510' target='_blank'>[Paper]</a> <a href='https://www.youtube.com/watch?v=nlZd-twMOaE' target='_blank'>[Video]</a> <a href='https://drive.google.com/file/d/1wUCKEy-h57z9rBwWE7OypIUFV_S3kWs6/view?usp=sharing' target='_blank'>[Slides]</a>

</div>

MV-JAR Overview

Masked Voxel Jigsaw and Reconstruction (MV-JAR) addresses the uneven distribution of LiDAR points using a Reversed-Furthest-Voxel-Sampling strategy, and combines two techniques for modeling voxel (MVJ) and point (MVR) distributions. We also introduce a new data-efficient 3D object detection benchmark on the Waymo dataset for more accurate evaluation of pre-training methods. Experiments demonstrate that MV-JAR significantly improves 3D detection performance across various data scales. 💥

News

Data-Efficient Benchmark on Waymo

Download

Usage

MMDetection3D Format

The information files provided in data_efficient_benchmark/* are processed according to MMDetection3D's data format, containing only annotations and object point clouds. Before using our benchmark, you must first download the original Waymo dataset and follow MMDetection3D's instructions to convert the data format to MMDetection3D's format. For more details, please refer to MMDetection3D's Prepare Waymo Dataset (v1.2).

To use our subsets, simply replace the waymo_infos_train.pkl and waymo_dbinfos_train.pkl with the corresponding files from our benchmark. For example, to use subset 0 with 5% of the scenes, replace them with waymo_infos_train_r_0.05_0.pkl and waymo_dbinfos_train_old_r_0.05_0.pkl, respectively.

Here are some notes:

Other Formats

You can convert the original Waymo data to any data format for different codebases, such as OpenPCDet, based on the provided filenames.

MV-JAR

We are cleaning the code and will release it soon. Stay tuned! 📣

Citation

If you find our work useful in your research, please cite:

@InProceedings{Xu_2023_CVPR,
    author    = {Xu, Runsen and Wang, Tai and Zhang, Wenwei and Chen, Runjian and Cao, Jinkun and Pang, Jiangmiao and Lin, Dahua},
    title     = {MV-JAR: Masked Voxel Jigsaw and Reconstruction for LiDAR-Based Self-Supervised Pre-Training},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    month     = {June},
    year      = {2023},
    pages     = {13445-13454}
}

Acknowledgements

We thank the contributors of MMDetection3D and the authors of SST for their great work!