Full python interactive 3D Gaussian Splatting viewer for real-time editing and analyzing.
Python
1,550
269 commits
updated May 20, 2026
Interactive 3D Gaussian Splatting viewer and editor.
Edit splats live, compare scenes side by side, attach to training runs, and inspect render data with Python snippets.
Demo video · Example scenes · Check out ganviz
Install uv with curl -LsSf https://astral.sh/uv/install.sh | sh and a matching CUDA Toolkit:
11.8,
12.6,
12.8, or
13.0.
git clone https://github.com/Florian-Barthel/splatviz.git
cd splatviz
Sync the environment with the CUDA extra for your system:
uv sync --extra cu118
uv sync --extra cu126
uv sync --extra cu128
uv sync --extra cu130
Then install the rasterizer:
uv pip install --no-build-isolation git+https://github.com/ashawkey/diff-gaussian-rasterization.git
On Windows, you may also need the 2022 Visual Studio C++ build tools.
winget install Microsoft.VisualStudio.2022.BuildTools
python run_main.py
If OpenGL picks the wrong version, set:
export MESA_GL_VERSION_OVERRIDE=3.3
Attach to a running 3DGS training process:
python run_main.py --mode=attach
By default, splatviz listens on 127.0.0.1:6007. Override with --host and
--port. For live editing during training, see
splatviz_network.
EditRun Python just before rendering to modify the Gaussian object live.
|
EvaluateInspect render variables and visualize values with histograms.
|
Version 1.3.0
uvVersion 1.2.0
Version 1.1.0
If splatviz helps your work, please cite:
@misc{barthel2024gaussian,
title={Gaussian Splatting Decoder for 3D-aware Generative Adversarial Networks},
author={Florian Barthel and Arian Beckmann and Wieland Morgenstern and Anna Hilsmann and Peter Eisert},
year={2024},
eprint={2404.10625},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
121 followers · starred Oct 2025
131 followers · starred May 2025
103 followers · starred Jul 2024
479 followers · starred Jul 2024
Full python interactive 3D Gaussian Splatting viewer for real-time editing and analyzing.
Python
1,550
269 commits
updated May 20, 2026
Interactive 3D Gaussian Splatting viewer and editor.
Edit splats live, compare scenes side by side, attach to training runs, and inspect render data with Python snippets.
Demo video · Example scenes · Check out ganviz
Install uv with curl -LsSf https://astral.sh/uv/install.sh | sh and a matching CUDA Toolkit:
11.8,
12.6,
12.8, or
13.0.
git clone https://github.com/Florian-Barthel/splatviz.git
cd splatviz
Sync the environment with the CUDA extra for your system:
uv sync --extra cu118
uv sync --extra cu126
uv sync --extra cu128
uv sync --extra cu130
Then install the rasterizer:
uv pip install --no-build-isolation git+https://github.com/ashawkey/diff-gaussian-rasterization.git
On Windows, you may also need the 2022 Visual Studio C++ build tools.
winget install Microsoft.VisualStudio.2022.BuildTools
python run_main.py
If OpenGL picks the wrong version, set:
export MESA_GL_VERSION_OVERRIDE=3.3
Attach to a running 3DGS training process:
python run_main.py --mode=attach
By default, splatviz listens on 127.0.0.1:6007. Override with --host and
--port. For live editing during training, see
splatviz_network.
EditRun Python just before rendering to modify the Gaussian object live.
|
EvaluateInspect render variables and visualize values with histograms.
|
Version 1.3.0
uvVersion 1.2.0
Version 1.1.0
If splatviz helps your work, please cite:
@misc{barthel2024gaussian,
title={Gaussian Splatting Decoder for 3D-aware Generative Adversarial Networks},
author={Florian Barthel and Arian Beckmann and Wieland Morgenstern and Anna Hilsmann and Peter Eisert},
year={2024},
eprint={2404.10625},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
121 followers · starred Oct 2025
131 followers · starred May 2025
103 followers · starred Jul 2024
479 followers · starred Jul 2024