A Gaussian Splatting Renderer and Tools package.
This repository primarily provides rendering capabilities for Gaussian Splatting models. It is developed as a component of the DISCOVERSE project.
For detailed usage within the simulation environment, see: https://github.com/TATP-233/DISCOVERSE
Python >= 3.10
uv add gaussian-renderer
# or: pip install gaussian-rendererFrom source:
git clone https://github.com/TATP-233/GaussainRenderer.git
cd GaussainRenderer
uv pip install .
# or: pip install .uv add "gaussian-renderer[viewer]" # OpenGL viewer (glfw, PyOpenGL)
uv add "gaussian-renderer[mujoco]" # MuJoCo integration
uv add "gaussian-renderer[motrix]" # MotrixSim integration
# Combine as needed
uv add "gaussian-renderer[viewer,mujoco]"
# or: pip install ".[viewer,mujoco]"gs-viewer — OpenGL viewer for .ply models
gs-viewer path/to/model.plyControls: Left mouse = rotate, Right/Middle = pan, Scroll = zoom, Up/Down = SH degree, Drag & drop = load file
gs-compress — Compress 3DGS PLY to SuperSplat format
gs-compress input.ply
gs-compress input.ply -o output.ply
gs-compress models/ # batchgs-transform — Apply translation/rotation/scale to a model
gs-transform input.ply -o output.ply -t 0 1 0 -s 2.0
gs-transform input.ply -r 0 0 0 1 # rotation quaternion xyzw
# --compress: save as compressed PLYuv run python -m gaussian_renderer.simple_viewer path/to/model.ply
uv run python -m gaussian_renderer.supersplat_compress input.ply
uv run python -m gaussian_renderer.transform_gs_model input.plyuv pip install ".[dev]"
# or: pip install ".[dev]"
make lint # ruff check
make format # ruff format
make typecheck # mypy
make test # pytest
make ci # all of the above@article{jia2025discoverse,
title={DISCOVERSE: Efficient Robot Simulation in Complex High-Fidelity Environments},
author={Yufei Jia and Guangyu Wang and Yuhang Dong and Junzhe Wu and Yupei Zeng and Haonan Lin and Zifan Wang and Haizhou Ge and Weibin Gu and Chuxuan Li and Ziming Wang and Yunjie Cheng and Wei Sui and Ruqi Huang and Guyue Zhou},
journal={arXiv preprint arXiv:2507.21981},
year={2025},
url={https://arxiv.org/abs/2507.21981}
}