ULSR-GS: Ultra Large-scale Surface Reconstruction Gaussian Splatting with Multi-View Geometric Consistency
This work addresses surface reconstruction in large-scale aerial photogrammetry, an incremental improvement over existing Gaussian Splatting methods.
The paper tackles the problem of surface extraction from ultra-large-scale aerial images using Gaussian Splatting, where existing methods fall short. It introduces ULSR-GS, which improves surface extraction accuracy on benchmark datasets for complex urban environments.
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.