In the domain of 3D scene representation, 3D Gaussian Splatting (3DGS) has emerged as a pivotal technology. However, its application to large-scale, high-resolution scenes (exceeding 4k$\times$4k pixels) is hindered by the excessive computational requirements for managing a large number of Gaussians. Addressing this, we introduce 'EfficientGS', an advanced approach that optimizes 3DGS for high-resolution, large-scale scenes. We analyze the densification process in 3DGS and identify areas of Gaussian over-proliferation. We propose a selective strategy, limiting Gaussian increase to key primitives, thereby enhancing the representational efficiency. Additionally, we develop a pruning mechanism to remove redundant Gaussians, those that are merely auxiliary to adjacent ones. For further enhancement, we integrate a sparse order increment for Spherical Harmonics (SH), designed to alleviate storage constraints and reduce training overhead. Our empirical evaluations, conducted on a range of datasets including extensive 4K+ aerial images, demonstrate that 'EfficientGS' not only expedites training and rendering times but also achieves this with a model size approximately tenfold smaller than conventional 3DGS while maintaining high rendering fidelity.

翻译：在三维场景表示领域，三维高斯泼溅（3D Gaussian Splatting, 3DGS）已成为一项关键技术。然而，该方法在应用于大规模高分辨率场景（超过4k×4k像素）时，因管理大量高斯分布所需的高昂计算成本而受到制约。针对这一问题，我们提出了一种名为"EfficientGS"的先进方法，旨在优化3DGS在高分辨率大规模场景中的表现。通过分析3DGS的密集化过程，我们识别出高斯分布过度增殖的区域，并提出一种选择性策略，将高斯分布的增长限制于关键基元，从而提升表示效率。此外，我们开发了一种剪枝机制，用于移除冗余的高斯分布——即那些仅作为相邻分布辅助元素的单元。为进一步提升性能，我们集成了球谐函数（Spherical Harmonics, SH）的稀疏阶递增技术，旨在缓解存储约束并降低训练开销。我们在包含4K+航拍图像在内的多个数据集上进行的实证评估表明，EfficientGS不仅能够加快训练和渲染速度，还能在保持高渲染保真度的同时，将模型规模缩减至传统3DGS的约十分之一。