This repository contains microscopy image data artificially generated by denoising diffusion probabilistic models ([preprint](https://arxiv.org/abs/2301.10227)). Simulated sketches indicating location and structural characteristics of cellular structures serves as a basis to allow for the automated generation of fully-annotated image data sets. Those data sets can be used to aid the training and application of deep learning-based image processing approaches. Code used for generation of those data sets is publicly available at [github](https://github.com/stegmaierj/DiffusionModelsForImageSynthesis).
If you are using code or data, please cite the following work:
@article{eschweiler2022celldiffusion,
title={Denoising Diffusion Probabilistic Models for Generation of Realistic Fully-Annotated Microscopy Image Data Sets},
author={Dennis Eschweiler and Johannes Stegmaier},
journal={arXiv/2301.10227},
year={2023}
}
