This is the official implementation of PowerGS.

Clone this repository recursively to include all submodules:

git clone --recursive https://github.com/horizon-research/PowerGS.git
cd PowerGS

We recommend using a virtual environment. You can use the provided install.sh script to install the necessary dependencies:

# Create a virtual environment (optional but recommended)
python3 -m venv env
source env/bin/activate

# Install dependencies
bash install.sh

Note: Ensure you have CUDA installed as the submodules require it for compilation.

To fit a scene, use the scripts/fit_a_scene.sh script. You need to provide the scene name, required quality, and a port for training:

bash scripts/fit_a_scene.sh <scene_name> <q_required> <port>

Example:

bash scripts/fit_a_scene.sh bicycle 0.99 6009

This project is licensed under the MIT License - see the LICENSE file for details.