LiDAR-Net

Yanwen Guo¹, Yuanqi Li¹, Dayong Ren¹, Xiaohong Zhang¹, Jiawei Li¹, Liang Pu¹, Changfeng Ma¹, Xiaoyu Zhan¹, Jie Guo¹, Mingqiang Wei², Yan Zhang¹, Piaopiao Yu¹, Shuangyu Yang¹, Donghao Ji¹, Huisheng Ye¹, Hao Sun¹, Yansong Liu¹, Yinuo Chen¹, Jiaqi Zhu¹, Hongyu Liu¹

LiDAR-Net is a new real-scanned indoor point cloud dataset, containing nearly 3.6 billion precisely point-level annotated points, covering an expansive area of 30,000 m². LiDAR-Net encompasses three prevalent daily environments, including learning scenes, working scenes, and living scenes. LiDAR-Net is characterized by its non-uniform point distribution, e.g., scanning holes and scanning lines. Additionally, it meticulously records and annotates scanning anomalies, including reflection noise and ghost. These anomalies stem from specular reflections on glass or metal, as well as distortions due to moving persons. LiDAR-Net’s realistic representation of non-uniform distribution and anomalies significantly enhances the training of deep learning models, leading to improved generalization in practical applications. Crucially, our research identifies several fundamental challenges in understanding indoor point clouds, contributing essential insights to future explorations in this field.

If you use the LiDAR-Net data or code please cite:

@inproceedings{guo2024lidarnet,
  title={LiDAR-Net: A Real-scanned 3D Point Cloud Dataset for Indoor Scenes},
  author={Guo, Yanwen and Li, Yuanqi and Ren, Dayong and Zhang, Xiaohong and Li, Jiawei and Pu, Liang and Ma, Changfeng and Zhan, Xiaoyu and Guo, Jie and Wei, Mingqiang and Zhang, Yan and Yu, Piaopiao and Yang, Shuangyu and Ji, Donghao and Ye, Huisheng and Sun, Hao and Liu, Yansong and Chen, Yinuo and Zhu, Jiaqi and Liu, Hongyu},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2024}
}