Yang Liu, Lue Fan, Naiyan Wang, Zhaoxiang Zhang, Junran Peng, Chuanchen Luo
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
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 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. 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/.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2404.01133")
get_code_for_paper("2404.01133")
have("2404.01133")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2404.01133.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2404.01133)
Connect an agent — have() is free.