EfficientGS: Streamlining Gaussian Splatting for Large-Scale High-Resolution Scene Representation
arxiv(2024)
摘要
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×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.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要