From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Network

This repository is for our TPAMI paper [arXiv].

Code is available at [PCDet].

Authors: Shaoshuai Shi, Zhe Wang, Jianping Shi, Xiaogang Wang, Hongsheng Li.

Introduction

In this work, we propose the part-aware and aggregation neural network (PartA2-Net). The whole framework consists of the part-aware stage and the part-aggregation stage. Firstly, the part-aware stage for the first time fully utilizes free-of-charge part supervisions derived from 3D ground-truth boxes to simultaneously predict high quality 3D proposals and accurate intra-object part locations. The predicted intra-object part locations within the same proposal are grouped by our new-designed RoI-aware point cloud pooling module, which results in an effective representation to encode the geometry-specific features of each 3D proposal. Then the part-aggregation stage learns to re-score the box and refine the box location by exploring the spatial relationship of the pooled intra-object part locations. At the time of submission (July-9 2019), our PartA2-Net outperforms all existing 3D detection methods and achieves new state-of-the-art on KITTI 3D object detection learderbaord by utilizing only the LiDAR point cloud data.

Code

The code of Part-A^2 has been released on PCDet.

Citation

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

@article{shi2019part,
    title={From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Network},
    author={Shi, Shaoshuai and Wang, Zhe and Shi, Jianping and Wang, Xiaogang and Li, Hongsheng},
    journal={arXiv preprint arXiv:1907.03670},
    year={2019}
}