---

LiDAR-RT: Gaussian-based Ray Tracing for Dynamic LiDAR Re-simulation

Chenxu Zhou* · Lvchang Fu* · Sida Peng^† · Yunzhi Yan · Zhanhua Zhang
Yong Chen · Jiazhi Xia · Xiaowei Zhou
CVPR 2025

📜 News

• [2025.4.17] The training and evaluation code has been released.
• [2025.2.27] 🎉 Our paper is accepted by CVPR 2025.

⚒️ Method

📦 Installation

Please refer to INSTALL.md for detailed installation instructions.

1. Environment Setup
2. Data Preparation

🚀 Training

Please refer to TRAIN.md for quick start of training.

🔭 Evaluation

Please refer to EVAL.md for evaluation and visualization.

❤️ Acknowledgments

This work is built upon the following codes, we would like to acknowledge these great works.

• EnvGS: Modeling View-Dependent Appearance with Environment Gaussian
• Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splatting
• 3D Gaussian Ray Tracing: Fast Tracing of Particle Scenes
• 3D Gaussian Splatting for Real-Time Radiance Field Rendering

📝 Citation

If you find this code useful for your research, please use the following BibTeX entry.

@inproceedings{zhou2024lidarrt,
    title={{LiDAR-RT}: Gaussian-based Ray Tracing for Dynamic LiDAR Re-simulation},
    author={Zhou, Chenxu and Fu, Lvchang and Peng, Sida and Yan, Yunzhi and Zhang, Zhanhua and Chen, Yong and Xia, Jiazhi and Zhou, Xiaowei},
    booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
    year={2025}
}

💌 Contact

If you have any question, please feel free to contact Chenxu Zhou or Github issues.