https://github.com/qcraftai/pillarnext
PillarNeXt: Rethinking Network Designs for 3D Object Detection in LiDAR Point Clouds (CVPR 2023)
https://github.com/qcraftai/pillarnext
3d-object-detection autonomous-driving lidar nuscenes perception point-cloud self-driving waymo-open-dataset
Last synced: about 1 month ago
JSON representation
PillarNeXt: Rethinking Network Designs for 3D Object Detection in LiDAR Point Clouds (CVPR 2023)
- Host: GitHub
- URL: https://github.com/qcraftai/pillarnext
- Owner: qcraftai
- License: other
- Created: 2023-05-05T21:45:53.000Z (almost 2 years ago)
- Default Branch: main
- Last Pushed: 2024-06-21T17:29:33.000Z (10 months ago)
- Last Synced: 2024-10-28T05:12:51.611Z (6 months ago)
- Topics: 3d-object-detection, autonomous-driving, lidar, nuscenes, perception, point-cloud, self-driving, waymo-open-dataset
- Language: Python
- Homepage:
- Size: 2.59 MB
- Stars: 191
- Watchers: 6
- Forks: 14
- Open Issues: 2
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# PillarNeXt: Rethinking Network Designs for 3D Object Detection in LiDAR Point Clouds
[Jinyu Li](https://konstantin5389.github.io/), [Chenxu Luo](https://chenxuluo.github.io/), [Xiaodong Yang](https://xiaodongyang.org/)
PillarNeXt: Rethinking Network Designs for 3D Object Detection in LiDAR Point Clouds, CVPR 2023
[[Paper]](https://arxiv.org/pdf/2305.04925.pdf) [[Poster]](docs/poster.pdf)
## Get Started
### Installation
Please refer to [INSTALL](docs/INSTALL.md) to set up environment and install dependencies (see detail in [Dockerfile](docker/Dockerfile)).
### Data Preparation
Please follow the instructions in [DATA](docs/DATA.md).
### Training and Evaluation
Please follow the instructions in [RUN](docs/RUN.md).
## Main Results
### nuScenes (Val)
| Model | mAP | NDS | Checkpoint
| ------| -----| ---- | -------------|
| PillarNeXt-B | 62.5 | 68.8 | [[Google Drive]](https://drive.google.com/file/d/16abCgt-yhRGnYHQ7M259yGMO0IRYpZ8o/view?usp=drive_link) [[Baidu Cloud]](https://pan.baidu.com/s/1TRsjgN1ys5-mAxM70l4hog?pwd=7skt)
### Waymo Open Dataset
|Split | #Frames | Veh L2 3D APH | Ped L2 3D APH | Cyc L2 3D APH |
| ---------| ---------|---------|---------|---------|
| Val | 1 | 69.8 | 69.8 | 69.6 |
| Val | 3 | 72.4 | 75.2 | 75.7 |
| Test| 3 | 75.8 | 76.0 | 70.6 |
## Citation
Please cite the following paper if this repo helps your research:
```
@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={IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
year={2023}
}
```
## Acknowledgement
We thank the authors for the multiple great open-sourced repos, including [Det3D](https://github.com/poodarchu/Det3D), [CenterPoint](https://github.com/tianweiy/CenterPoint) and [OpenPCDet](https://github.com/open-mmlab/OpenPCDet).
## License
Copyright (C) 2023 QCraft. All rights reserved. Licensed under the [CC BY-NC-SA 4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/legalcode) (Attribution-NonCommercial-ShareAlike 4.0 International). The code is released for academic research use only. For commercial use, please contact [[email protected]]([email protected]).