Robust and Efficient 3D Gaussian Splatting for Urban Scene Reconstruction

Zhensheng Yuan1, 2   Haozhi Huang1   Zhen Xiong1   Di Wang1*   Guanghua Yang1*  
1Jinan University    2University of Macau
   zhensheng@stu2022.jnu.edu.cn   hzhuang@jnu.edu.cn   acxz2000@stu2022.jnu.edu.cn   diwang@jnu.edu.cn   ghyang@jnu.edu.cn  
*Corresponding author
ICCV 2025
Paper arXiv Code (Coming Soon)

Abstract

We present a framework that enables fast reconstruction and real-time rendering of urban-scale scenes while maintaining robustness against appearance variations across multi-view captures. Our approach begins with scene partitioning for parallel training, employing a visibility-based image selection strategy to optimize training efficiency. A controllable level-of-detail (LOD) strategy explicitly regulates Gaussian density under a user-defined budget, enabling efficient training and rendering while maintaining high visual fidelity. The appearance transformation module mitigates the negative effects of appearance inconsistencies across images while enabling flexible adjustments. Additionally, we utilize enhancement modules, such as depth regularization, scale regularization, and antialiasing, to improve reconstruction fidelity. Experimental results demonstrate that our method effectively reconstructs urban-scale scenes and outperforms previous approaches in both efficiency and quality.

Comparison with SOTA





BibTeX


@misc{yuan2025robustefficient3dgaussian,
      title={Robust and Efficient 3D Gaussian Splatting for Urban Scene Reconstruction}, 
      author={Zhensheng Yuan and Haozhi Huang and Zhen Xiong and Di Wang and Guanghua Yang},
      year={2025},
      eprint={2507.23006},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2507.23006}, 
}