CityGaussian: Real-time High-quality Large-Scale Scene Rendering with Gaussians

Abstract

The advancement of real-time 3D scene reconstruction and novel view synthesis has been significantly propelled by 3DGS. However, effectively training large-scale 3DGS and rendering it in real-time across various scales remains challenging.

This paper introduces CityGaussian (CityGS), which employs a novel divideand-conquer training approach and Level-of-Detail (LoD) strategy for efficient large-scale 3DGS training and rendering.

Specifically, the global scene prior and adaptive training data selection enables efficient training and seamless fusion. Based on fused Gaussian primitives, we generate different detail levels through compression, and realize fast rendering across various scales through the proposed block-wise detail levels selection and aggregation strategy.

全局场景先验和自适应的训练数据选择能够实现高效的训练和无缝融合。在融合高斯图元的基础上，通过压缩生成不同的细节层次，并通过提出的分块细节层次选择和聚合策略，实现不同尺度的快速绘制。

Extensive experimental results on large-scale scenes demonstrate that our approach attains state-of-theart rendering quality, enabling consistent real-time rendering of largescale scenes across vastly different scales.

project page

Figure

Fi