This repo provides the code to replicate the experiments in the paper:

Image Generation With Neural Cellular Automatas arxiv link

In this paper, we propose a novel approach to generate images (or other artworks) by using neural cellular automatas (NCAs). Rather than training NCAs based on single images one by one, we combined the idea of variational autoencoders (VAEs), and hence explored some applications, such as image restoration and style fusion.

Welcome to cite our work:

@article{chen2020image,
  title={Image Generation With Neural Cellular Automatas},
  author={Chen, Mingxiang and Wang, Zhecheng},
  journal={arXiv preprint arXiv:2010.04949},
  year={2020}
}

The trained models can be downloaded from:

https://drive.google.com/drive/folders/1sGXbnsZCF4w3FhvTi0J6bXBKlP-XebmY?usp=sharing