While Gaussian Splatting (GS) demonstrates efficient and high-quality scene rendering and small area surface extraction ability, it falls short in handling large-scale aerial image surface extraction tasks. To overcome this, we present ULSR-GS, a framework dedicated to high-fidelity surface extraction in ultra-large-scale scenes, addressing the limitations of existing GS-based mesh extraction methods. Specifically, we propose a point-to-photo partitioning approach combined with a multi-view optimal view matching principle to select the best training images for each sub-region. Additionally, during training, ULSR-GS employs a densification strategy based on multi-view geometric consistency to enhance surface extraction details. Experimental results demonstrate that ULSR-GS outperforms other state-of-the-art GS-based works on large-scale aerial photogrammetry benchmark datasets, significantly improving surface extraction accuracy in complex urban environments. Project page: https://ulsrgs.github.io.
@article{arxiv.2412.01402,
title = {ULSR-GS: Ultra Large-scale Surface Reconstruction Gaussian Splatting with Multi-View Geometric Consistency},
author = {Zhuoxiao Li and Shanliang Yao and Taoyu Wu and Yong Yue and Wufan Zhao and Rongjun Qin and Angel F. Garcia-Fernandez and Andrew Levers and Xiaohui Zhu},
journal= {arXiv preprint arXiv:2412.01402},
year = {2025}
}