Skip to main content

A Gaussian Splatting Renderer and Tools

Project description

Gaussian Renderer

A Gaussian Splatting Renderer and Tools package.

中文文档

This repository primarily provides rendering capabilities for Gaussian Splatting models. It is developed as a component of the DISCOVERSE project.

For detailed usage of the renderer within the simulation environment, please refer to: https://github.com/TATP-233/DISCOVERSE

Installation

Basic Installation

To install the core package (without viewer dependencies):

pip install gaussian-renderer

Or from source:

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

With Viewer Support

To install with viewer dependencies (glfw, PyOpenGL):

pip install ".[viewer]"

With MuJoCo Support (Optional)

To use MuJoCo-related functionality (e.g., modules in gaussian_renderer/gs_renderer_mujoco.py), install the optional MuJoCo extra:

pip install ".[mujoco]"

With MotrixSim Support (Optional)

To enable MotrixSim integration, install the optional extra:

pip install ".[motrix]"

Combine Extras

You can combine extras as needed, for example:

# Viewer + MuJoCo
pip install ".[viewer,mujoco]"

# Viewer + MotrixSim
pip install ".[viewer,motrix]"

Usage

This package provides three command-line tools:

1. Simple Viewer (gs-viewer)

A simple OpenGL-based viewer for Gaussian Splatting models (.ply files).

Usage:

# Open a specific model
gs-viewer path/to/model.ply

# Or just run and drag-drop files
gs-viewer

Controls:

  • Left Mouse: Rotate
  • Right/Middle Mouse: Pan
  • Scroll: Zoom
  • Up/Down Key: Adjust SH Degree
  • Drag & Drop: Load PLY file

2. SuperSplat Compressor (gs-compress)

Compress 3DGS PLY models to the SuperSplat format.

Usage:

# Compress a single file
gs-compress input.ply

# Specify output file
gs-compress input.ply -o output.ply

# Batch compress a directory
gs-compress models/

3. Model Transformer (gs-transform)

Apply transformations (translation, rotation, scaling) to Gaussian Splatting models.

Usage:

# Basic transformation
gs-transform input.ply -o output.ply -t 0 1 0 -s 2.0

# Rotate (quaternion xyzw)
gs-transform input.ply -r 0 0 0 1

# Options:
# -t x y z      : Translation vector
# -r x y z w    : Rotation quaternion
# -s scale      : Scale factor
# --compress    : Save as compressed PLY

Python API

You can also use the tools as Python modules:

python -m gaussian_renderer.simple_viewer path/to/model.ply
python -m gaussian_renderer.supersplat_compress input.ply
python -m gaussian_renderer.transform_gs_model input.ply

Citation

If you find this package helpful, please consider citing our work:

@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}
}

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

gaussian_renderer-0.1.8.tar.gz (31.3 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

gaussian_renderer-0.1.8-py3-none-any.whl (44.4 kB view details)

Uploaded Python 3

File details

Details for the file gaussian_renderer-0.1.8.tar.gz.

File metadata

  • Download URL: gaussian_renderer-0.1.8.tar.gz
  • Upload date:
  • Size: 31.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.10.16

File hashes

Hashes for gaussian_renderer-0.1.8.tar.gz
Algorithm Hash digest
SHA256 d34a028568be2cd3a387aa44ce5cad42a7f4522b9bb51b398a8879091216f831
MD5 b3fadbaa9c0b4076513289afde3a6baa
BLAKE2b-256 f6ef4ff89babb9abe2255a93676dc88891c3416cf3293c80ee6c4ca348120537

See more details on using hashes here.

File details

Details for the file gaussian_renderer-0.1.8-py3-none-any.whl.

File metadata

File hashes

Hashes for gaussian_renderer-0.1.8-py3-none-any.whl
Algorithm Hash digest
SHA256 f23819217f1fdbdaa72a092b6d1d67aeb9a2bf81342d1103bd894c6390bdf6ac
MD5 09160970fd5f7dcf2e56f9d7689293bb
BLAKE2b-256 8be568038fc761768a416d0842484a44547bccd56191384d1a59377208b30f63

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page