Semantic Diffusion Posterior Sampling for Cardiac Ultrasound Dehazing
Eindhoven University of Technology, the Netherlands
### Installation
The algorithm is implemented using Keras with JAX backend. Furthermore it heavily relies on the [zea ultrasound library](https://github.com/tue-bmd/zea).
Either install the following in your Python environment, or use the [Dockerfile](./Dockerfile) provided in this repository.
```bash
# requires Python>=3.10
pip install tyro optuna zea==0.0.4
pip install -U "jax[cuda12]"
```
> [!NOTE]
> Although the code was primarily tested with JAX as the Keras backend, TensorFlow and PyTorch should also work.
### Running the algorithm
Some example images are downloaded in the [./assets](./assets) folder. The models are automatically downloaded from the [Hugging Face Model Hub](https://huggingface.co/collections/tristan-deep/semantic-diffusion-posterior-sampling-for-cardiac-ultrasound-68a70559a7f719c7e6bd5788).
```bash
python main.py --input-folder ./assets --output-folder ./temp
```