Jinyu Li, Chenxu Luo, Xiaodong Yang
PillarNeXt: Rethinking Network Designs for 3D Object Detection in LiDAR Point Clouds, CVPR 2023
[Paper] [Poster]
Please refer to INSTALL to set up environment and install dependencies. Please refer to the Dockerfile for detail.
Please refer to DATA for detail.
Please refer to Training for detail.
Model | mAP | NDS | checkpoint |
---|---|---|---|
PillarNeXt-B | 62.5 | 68.8 | [Google Drive] [Baidu Yunpan](7skt) |
Split | #frames | Veh L2 | Ped L2 | Cyc L2 |
---|---|---|---|---|
val | 1 | 67.8 | 69.8 | 69.6 |
val | 3 | 72.4 | 75.2 | 75.7 |
test | 3 | 75.8 | 76.0 | 70.6 |
All numbers are 3D mAPH.
If you find this code useful in your research, please consider citing:
@inproceedings{li2023pillarnext,
title={PillarNeXt: Rethinking Network Designs for 3D Object Detection in LiDAR Point Clouds},
author={Li, Jinyu and Luo, Chenxu and Yang, Xiaodong},
booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
pages={17567--17576},
year={2023}
}
This project is not possible without multiple great opensourced codebases. We list some notable examples below.