#163 · Primary category: Computer Vision
CityGaussian
[ECCV`24&ICLR`25] CityGaussian Series for High-quality Large-Scale Scene Reconstruction with Gaussians
Project last updated:08/16/26
GitHub Stars
1.3K
Forks
110
Contributors
7
License
Other
Why we included this project
Most Gaussian Splatting examples stick to a single object or a small room, but this project is aimed at outdoor and urban scenes at city scale. It combines two peer-reviewed methods, one for real-time rendering of large scenes and a follow-up that improves geometric accuracy, into a single pipeline. Multi-GPU reconstruction keeps memory use controllable, so you don't need a massive cluster to process big captures, and mesh extraction is available when you need geometry-aware output. The reference implementations are useful for reproducing the papers and for prototyping photorealistic digital twins of real environments. The main branch has been rebased onto Gaussian Lightning and includes support for VGGT-X, which makes it easier to integrate into an existing workflow.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
opencv
Open Source Computer Vision Library
RuView
π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.
PaddleOCR
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
MinerU
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
tesseract
Tesseract Open Source OCR Engine (main repository)