by Yu Zheng, Xiuwei Xu, Jie Zhou, and Jiwen Lu#.
This repository is built for the official implementation of:
PointRas: Uncertainty-Aware Multi-Resolution Learning for Point Cloud Segmentation (TIP2022) [link]
If you find our work useful in your research, please consider citing:
@article{zheng2022pointras,
title={PointRas: Uncertainty-aware multi-resolution learning for point cloud segmentation},
author={Zheng, Yu and Xu, Xiuwei and Zhou, Jie and Lu, Jiwen},
journal={IEEE Transactions on Image Processing},
volume={31},
pages={6002--6016},
year={2022},
publisher={IEEE}
}
We provide scripts for different baseline methods:
-
PointConv-Ras: PointConv incorporated with our PointRas.
-
ELGS-Ras: ELGS incorporated with our PointRas.
You can find the instructions for running these tasks in the above corresponding folders.
You are welcome to send pull requests or share some ideas with us. Contact information: Yu Zheng (zhengyu19 AT mails.tsinghua.edu.cn).
Many thanks for the flexible code base from PointNet++, PointConv and ELGS, whose citations are:
@article{qi2017pointnet++,
title={Pointnet++: Deep hierarchical feature learning on point sets in a metric space},
author={Qi, Charles Ruizhongtai and Yi, Li and Su, Hao and Guibas, Leonidas J},
journal={Advances in neural information processing systems},
volume={30},
year={2017}
}
@inproceedings{wu2019pointconv,
title={Pointconv: Deep convolutional networks on 3d point clouds},
author={Wu, Wenxuan and Qi, Zhongang and Fuxin, Li},
booktitle={Proceedings of the IEEE/CVF Conference on computer vision and pattern recognition},
pages={9621--9630},
year={2019}
}
@article{wang2019exploiting,
title={Exploiting local and global structure for point cloud semantic segmentation with contextual point representations},
author={Wang, Xu and He, Jingming and Ma, Lin},
journal={Advances in Neural Information Processing Systems},
volume={32},
year={2019}
}
