#2 · Primary category: 3D Generation & Asset Creation

LichtFeld-Studio

computer-graphics computer-vision cuda gaussian-splatting optimization

Train, inspect, edit, automate, and export 3D Gaussian Splatting scenes from a single native application.

Project last updated:08/29/26

GitHub Stars

3.6K

Forks

435

Contributors

57

License

GPL-3.0

Why we included this project

Most 3D Gaussian Splatting workflows force you to juggle a training script, a separate viewer, and a one-off editing tool. LichtFeld Studio pulls the whole job into one native desktop app: you can train a scene from a COLMAP dataset, watch the reconstruction update in real time, select and transform gaussian subsets, and export the result as PLY, SOG, or SPZ without switching programs. Researchers get MCMC optimization and support for distorted camera models, so reconstruction quality can be iterated on rather than blocked by tooling. The Python plugin system, embedded Python, and MCP-based automation let you fold it into larger pipelines while keeping a visual workspace for the scene work itself. Prebuilt releases target Windows and it needs an NVIDIA GPU, so teams on other setups should expect to build from source.

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