HUG: Hierarchical Urban Gaussian Splatting with Block-Based Reconstruction for Large-Scale Aerial Scenes
This addresses efficiency and quality issues in 3D reconstruction for urban planning or mapping applications, but it is incremental as it builds on existing 3DGS methods.
The paper tackled the problem of excessive memory consumption, slow training, and degraded rendering quality when applying 3D Gaussian Splatting (3DGS) to large-scale aerial urban scenes, resulting in a method that achieves state-of-the-art results on one synthetic and four real-world datasets.
3DGS is an emerging and increasingly popular technology in the field of novel view synthesis. Its highly realistic rendering quality and real-time rendering capabilities make it promising for various applications. However, when applied to large-scale aerial urban scenes, 3DGS methods suffer from issues such as excessive memory consumption, slow training times, prolonged partitioning processes, and significant degradation in rendering quality due to the increased data volume. To tackle these challenges, we introduce \textbf{HUG}, a novel approach that enhances data partitioning and reconstruction quality by leveraging a hierarchical neural Gaussian representation. We first propose a visibility-based data partitioning method that is simple yet highly efficient, significantly outperforming existing methods in speed. Then, we introduce a novel hierarchical weighted training approach, combined with other optimization strategies, to substantially improve reconstruction quality. Our method achieves state-of-the-art results on one synthetic dataset and four real-world datasets.