Coming soon - Links will be updated on the week of Dec 15th
Splatkit enables the creation and sharing of dynamic gaussian splats by providing a powerful and easy-to-use toolset. Splatkit leverages the latest techniques from the research community.
- Visit our Learn Splatkit course to get started with Splatkit.
- Visit the Splatkit Showcase to see what others have built with Splatkit
Visit https://splatkit.org/docs to view the full documentation.
The Splatkit community can be found on GitHub Discussions where you can ask questions, voice ideas, and share your projects with other people.
To chat with other community members you can also join the Splatkit Discord server.
Splatkit is built on multiple projects from our community. The currently tracked projects are:
- DGS
- The encoder/decoder for the core file format,
.dgs. - Written in C, with python bindings.
pip install dgs-py(v1.1.1).
- The encoder/decoder for the core file format,
- DGS-JS
- Javascript bindings for
DGS, as well as a web-based renderer for.dgsfiles. npm install dgs-js(v1.1.2).
- Javascript bindings for
- DDGS
- The differentiable renderer for training
.dgsfiles. - Written in CUDA and C++, integrated with PyTorch.
- Must be built from source, pip package to come (
v0.0.1).
- The differentiable renderer for training