The advancement of real-time 3D scene reconstruction and novel view synthesis has been significantly propelled by 3D Gaussian Splatting (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 divide-and-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. 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. Our project page is available at https://dekuliutesla.github.io/citygs/.
CityGaussian (CityGS) introduces a novel method for high-fidelity rendering of large-scale scenes like cities in real-time, using a divide-and-conquer strategy for 3D Gaussian Splatting training and a Level-of-Detail (LoD) strategy.
The divide-and-conquer approach enables efficient management of GPU memory and computational resources by partitioning large scenes into smaller blocks for training.
A novel LoD strategy reduces GPU memory usage and computation time, ensuring seamless real-time performance across different viewing scales.
Extensive experiments demonstrate CityGS's superior rendering quality and speed over state-of-the-art methods, suggesting its practical benefits for VR/AR, autonomous driving, and urban planning.
The paper introduces an innovative approach titled CityGaussian (CityGS), aimed at significantly enhancing the rendering fidelity for large-scale scenes such as cities, combined with the efficiency required for real-time performance across varying scales. The method is predicated on the utilization of a novel divide-and-conquer strategy for effective large-scale 3D Gaussian Splatting (3DGS) training, and a Level-of-Detail (LoD) strategy that ensures seamless and fast rendering across various scales. This approach effectively addresses challenges associated with training and memory overheads in large-scale scene reconstruction, paving the way for consistent real-time rendering without compromising visual quality.
CityGS endeavors to remedy the limitations of existing 3D Gaussian Splatting techniques when applied to large-scale scenes. The paper's contributions are articulated through a series of methodological innovations and technical advancements:
The efficacy of CityGS is substantiated through extensive experiments conducted on large-scale scenes, demonstrating superior rendering quality and real-time performance. The experiments reveal that:
The research offers significant theoretical and practical implications for the field of large-scale scene rendering:
In conclusion, CityGaussian represents a significant advancement in the rendering of large-scale scenes, providing an effective solution to the challenges of training scalability and rendering performance. Its innovative divide-and-conquer training approach, coupled with the strategic implementation of Level-of-Detail, ushers in a new era of efficient, high-fidelity scene rendering suitable for real-time applications. This work not only demonstrates outstanding performance in current benchmarks but also sets the stage for future explorations into the efficient rendering of expansive virtual worlds.