Gaussian Renderer

高斯泼溅（Gaussian Splatting）渲染器及工具包。

本仓库主要提供高斯泼溅模型的渲染功能，最初作为一代工作 DISCOVERSE 的高斯渲染组件开发。

在 DISCOVERSE 的基础上，GaussianRenderer 进一步支持二代工作 gs_playground，提供 Rigid-Link Gaussian Kinematics 相关的高斯渲染组件。

关于在仿真环境中的详细使用方法，请参考：https://github.com/TATP-233/DISCOVERSE

环境要求

Python >= 3.10

安装

uv add gaussian-renderer
# 或：pip install gaussian-renderer

从源码安装：

git clone https://github.com/TATP-233/GaussainRenderer.git
cd GaussainRenderer
uv pip install .
# 或：pip install .

可选依赖

uv add "gaussian-renderer[viewer]"   # OpenGL 查看器（glfw, PyOpenGL）
uv add "gaussian-renderer[mujoco]"   # MuJoCo 集成
uv add "gaussian-renderer[motrix]"   # MotrixSim 集成

# 按需组合
uv add "gaussian-renderer[viewer,mujoco]"
# 或：pip install ".[viewer,mujoco]"

使用

命令行工具

gs-viewer — OpenGL 查看器，支持 .ply 模型

gs-viewer path/to/model.ply

控制：左键旋转，右键/中键平移，滚轮缩放，上/下键调整 SH 阶数，拖放加载文件

gs-compress — 将 3DGS PLY 压缩为 SuperSplat 格式

gs-compress input.ply
gs-compress input.ply -o output.ply
gs-compress models/          # 批量处理

gs-transform — 对模型应用平移/旋转/缩放

gs-transform input.ply -o output.ply -t 0 1 0 -s 2.0
gs-transform input.ply -r 0 0 0 1   # 旋转四元数 xyzw
# --compress: 保存为压缩 PLY

Python API

uv 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.ply

开发

uv pip install ".[dev]"
# 或：pip install ".[dev]"
make lint       # ruff 检查
make format     # ruff 格式化
make typecheck  # mypy
make test       # pytest
make ci         # 以上全部

引用

如果本项目对您的研究有帮助，请考虑引用：

@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}
}

@article{jia2026gsplayground,
      title={GS-Playground: A High-Throughput Photorealistic Simulator for Vision-Informed Robot Learning},
      author={Yufei Jia and Heng Zhang and Ziheng Zhang and Junzhe Wu and Mingrui Yu and Zifan Wang and Dixuan Jiang and Zheng Li and Chenyu Cao and Zhuoyuan Yu and Xun Yang and Haizhou Ge and Yuchi Zhang and Jiayuan Zhang and Zhenbiao Huang and Tianle Liu and Shenyu Chen and Jiacheng Wang and Bin Xie and Xuran Yao and Xiwa Deng and Guangyu Wang and Jinzhi Zhang and Lei Hao and Zhixing Chen and Yuxiang Chen and Anqi Wang and Hongyun Tian and Yiyi Yan and Zhanxiang Cao and Yizhou Jiang and Hanyang Shao and Yue Li and Lu Shi and Bokui Chen and Wei Sui and Hanqing Cui and Yusen Qin and Ruqi Huang and Lei Han and Tiancai Wang and Guyue Zhou},
      journal={arXiv preprint arXiv:2604.25459},
      year={2026},
      url={https://arxiv.org/abs/2604.25459}
}