Image Generation With Neural Cellular Automatas

TL;DR

This paper introduces a new method for image generation using neural cellular automatas combined with variational autoencoders, enabling applications like image restoration and style fusion.

Contribution

It presents a novel integration of NCAs with VAEs, expanding their application scope beyond traditional image generation.

Findings

Demonstrated successful image restoration using the proposed model

Enabled style fusion through neural cellular automatas

Provided open-source code for reproducibility

Abstract

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 with variational autoencoders (VAEs), and hence explored some applications, such as image restoration and style fusion. The code for model implementation is available online.