A free and open source implementation of 3D gaussian splatting, written in C++. It's based on splatfacto and focuses on being portable, lean and fast.
OpenSplat takes camera poses + sparse points and computes a scene file (.ply) that can be later imported for viewing, editing and rendering in other software.
Requirements:
- CUDA: Make sure you have the CUDA compiler (
nvcc) in your PATH and thatnvidia-smiis working. https://docs.nvidia.com/cuda/cuda-installation-guide-linux/index.html - libtorch: Visit https://pytorch.org/get-started/locally/ and select your OS, for package select "LibTorch". Make sure to match your version of CUDA if you want to leverage GPU support in libtorch.
- OpenCV:
sudo apt install libopencv-devshould do it.
Then:
git clone https://github.com/pierotofy/OpenSplat OpenSplat
cd OpenSplat
mkdir build && cd build
cmake -DCMAKE_PREFIX_PATH=/path/to/libtorch/ .. && make -j$(nproc)The software has been tested on Ubuntu 20.04, but with some or minimal changes, it should build on Windows and MacOS (help us by opening a PR?).
To get started, download a dataset and extract it to a folder: [ banana ]
Then run:
./opensplat /path/to/banana -n 2000
[...]
Wrote splat.plyThe output splat.ply can then be dragged and dropped in one of the many viewers such as https://playcanvas.com/viewer. You can also edit/cleanup the scene using https://playcanvas.com/supersplat/editor
To run on your own data, choose the path to an existing nerfstudio project. The project must have sparse points included (random initialization is not supported, see pierotofy#7). You can generate nerfstudio projects from COLMAP by using nerfstudio's ns-process-data command: https://docs.nerf.studio/quickstart/custom_dataset.html
We have plans to add support for reading COLMAP projects directly in the near future. See pierotofy#1
There's several parameters you can tune. To view the full list:
./opensplat --helpWe recently released OpenSplat, so there's lots of work to do.
- Support for running on AMD cards
- Support for running on CPU-only
- Improve speed / reduce memory usage
- Distributed computation using multiple machines
- Real-time training viewer output
- Compressed scene outputs
- Your ideas?
https://github.com/pierotofy/OpenSplat/issues?q=is%3Aopen+is%3Aissue+label%3Aenhancement
We welcome contributions! Pull requests are welcome.
The code in this repository, unless otherwise noted, is licensed under the AGPLv3.
The code from splatfacto is originally licensed under the Apache 2.0 license and is © 2023 The Nerfstudio Team.