_README_ #2

This dataset is shared in conjunction with a manuscript, titled "MozzaVID: Mozzarella Volumetric Image Dataset"

The data is provided in three versions/sizes (Small, Base, Large). The "models" folder enables recreating the results reported in the paper.

For details, see below liks:
1. Webpage of the project - https://papieta.github.io/MozzaVID/
2. Manuscript - https://arxiv.org/abs/2412.04880
3. GitHub repository (data loaders, examples) - https://github.com/PaPieta/MozzaVID/tree/main


To download the data, click on a chosen file/folder, then click the download button in the top right corner.

Alternatively, the data can be easily fetched through the command line, for example with:
> wget https://archive.compute.dtu.dk/downloads/public/projects/MozzaVID/[Small, Base, Large].zip


If you are low on disk space, you can stream the dataset splits during training using our WebDataset setup on HuggingFace (check our GitHub for details):
https://huggingface.co/datasets/dtudk/[MozzaVID_Small, MozzaVID_Base, MozzaVID_Large]

If you use our data, please consider citing our work:

@misc{pieta2024b,
      title={MozzaVID: Mozzarella Volumetric Image Dataset}, 
      author={Pawel Tomasz Pieta and Peter Winkel Rasmussen and Anders Bjorholm Dahl and Jeppe Revall Frisvad and Siavash Arjomand Bigdeli and Carsten Gundlach and Anders Nymark Christensen},
      year={2024},
      howpublished={arXiv:2412.04880 [cs.CV]},
      eprint={2412.04880},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2412.04880}, 
}