💦 OpenSplat

A free and open source implementation of 3D gaussian splatting written in C++, focused on being portable, lean and fast.

OpenSplat takes camera poses + sparse points in COLMAP or nerfstudio project format and computes a scene file (.ply) that can be later imported for viewing, editing and rendering in other software.

Commercial use allowed and encouraged under the terms of the AGPLv3. ✅

Build

Requirements:

CUDA: Make sure you have the CUDA compiler (nvcc) in your PATH and that nvidia-smi is 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-dev should 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 and Windows. With some changes it could run on macOS (help us by opening a PR?).

Build Docker Image

Navigate to the root directory of OpenSplat repo that has Dockerfile and run the following command to build the Docker image:

docker build -t opensplat .

The -t flag and other --build-arg let you tag and further customize your image across different ubuntu versions, CUDA/libtorch stacks, and hardware accelerators. For example, to build an image with Ubuntu 22.04, CUDA 12.1.1, libtorch 2.2.1, and support for CUDA architectures 7.0 and 7.5, run the following command:

docker build \
  -t opensplat:ubuntu-22.04-cuda-12.1.1-torch-2.2.1 \
  --build-arg UBUNTU_VERSION=22.04 \
  --build-arg CUDA_VERSION=12.1.1 \
  --build-arg TORCH_VERSION=2.2.1 \
  --build-arg TORCH_CUDA_ARCH_LIST="7.0;7.5" \
  --build-arg CMAKE_BUILD_TYPE=Release .

Run

To get started, download a dataset and extract it to a folder: [ banana ] [ train ] [ truck ]

Then run:

./opensplat /path/to/banana -n 2000
[...]
Wrote splat.ply

The 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 COLMAP or nerfstudio project. The project must have sparse points included (random initialization is not supported, see pierotofy#7).

There's several parameters you can tune. To view the full list:

./opensplat --help

Project Goals

We 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

Contributing

We welcome contributions! Pull requests are welcome.

GPU Memory Notes

A single gaussian takes ~2000 bytes of memory, so currenly you need ~2GB of GPU memory for each million gaussians.

Credits

The methods used in OpenSplat are originally based on splatfacto.

License

The code in this repository, unless otherwise noted, is licensed under the AGPLv3.

dogcaicai / OpenSplat