AIOct 10, 2020
Image Generation With Neural Cellular Automatas
arXiv:2010.04949v22 citationsHas Code
Originality Synthesis-oriented
AI Analysis
This work addresses image generation and manipulation for creative or restoration tasks, but it appears incremental as it builds on existing NCA and VAE methods.
The paper tackles image generation by combining neural cellular automatas (NCAs) with variational autoencoders (VAEs), enabling applications like image restoration and style fusion.
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.