Semantic2D: Enabling Semantic Scene Understanding with 2D Lidar Alone: Dataset

# Semantic2D Dataset

A 2D lidar semantic segmentation dataset for mobile robotics applications. This is the first publicly available 2D lidar semantic segmentation dataset, featuring point-wise annotations for nine indoor object categories across twelve distinct environments.

**Associated Paper:** *Semantic2D: Enabling Semantic Scene Understanding with 2D Lidar Alone*
**Authors:** Zhanteng Xie, Yipeng Pan, Yinqiang Zhang, Jia Pan, Philip Dames
**Institutions:** The University of Hong Kong, Temple University

**Video:** https://youtu.be/P1Hsvj6WUSY
**GitHub:** https://github.com/TempleRAIL/semantic2d

---

## Citation

```bibtex
@article{xie2026semantic2d,
  title={Semantic2D: Enabling Semantic Scene Understanding with 2D Lidar Alone},
  author={Xie, Zhanteng and Pan, Yipeng and Zhang, Yinqiang and Pan, Jia and Dames, Philip},
  journal={arXiv preprint arXiv:2409.09899},
  year={2026}
}
```

## Contact

- Zhanteng Xie: zhanteng@hku.hk