This repository contains the implementation of PLON, which generates odometry and loop closure information only using three-dimensional laser range scans.
Developed by Liang Wang, Chen Fu and Yihuan Zhang.
PLON is built upon RangeNet++ and SqueezeNetV2. For more details, we refer to the original project websites RangeNet++.
An example of using PLON:
TODO:here require a gif pic.
related work:
@inproceedings{li2019net,
title={Lo-net: Deep real-time lidar odometry},
author={Li, Qing and Chen, Shaoyang and Wang, Cheng and Li, Xin and Wen, Chenglu and Cheng, Ming and Li, Jonathan},
booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
pages={8473--8482},
year={2019}
}
@article{wang2020dmlo,
title={DMLO: Deep Matching LiDAR Odometry},
author={Wang, Naiyan and Li, Zhichao},
journal={arXiv preprint arXiv:2004.03796},
year={2020}
}
@article{cho2019deeplo,
title={Deeplo: Geometry-aware deep lidar odometry},
author={Cho, Younggun and Kim, Giseop and Kim, Ayoung},
journal={arXiv preprint arXiv:1902.10562},
year={2019}
}
@inproceedings{liu2019flownet3d,
title={Flownet3d: Learning scene flow in 3d point clouds},
author={Liu, Xingyu and Qi, Charles R and Guibas, Leonidas J},
booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
pages={529--537},
year={2019}
}
@article{chen2020survey,
title={A Survey on Deep Learning for Localization and Mapping: Towards the Age of Spatial Machine Intelligence},
author={Chen, Changhao and Wang, Bing and Lu, Chris Xiaoxuan and Trigoni, Niki and Markham, Andrew},
journal={arXiv preprint arXiv:2006.12567},
year={2020}
}
nothing published yet.
ubuntu 18.04 docker environment TODO: more detailed instructions.
nothing official yet.
Copyright 2020, Liang Wang, Chen Fu, Yihuan Zhang.
This project is free software made available under the MIT License. For details see the LICENSE file.
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent