Multi-Texture Synthesis through Signal Responsive Neural Cellular Automata

TL;DR

This paper introduces a unified neural cellular automaton that can generate, interpolate, and edit multiple textures from a single trained model, enhancing flexibility and usability in texture synthesis.

Contribution

The authors develop a single NCA model capable of learning and generating multiple textures from individual examples, with embedded genomic signals enabling interpolation and editing.

Findings

Single NCA can generate multiple textures from one model

Genomic signals enable texture interpolation and editing

The approach maintains regenerative capabilities of NCA

Abstract

Neural Cellular Automata (NCA) have proven to be effective in a variety of fields, with numerous biologically inspired applications. One of the fields, in which NCAs perform well is the generation of textures, modelling global patterns from local interactions governed by uniform and coherent rules. This paper aims to enhance the usability of NCAs in texture synthesis by addressing a shortcoming of current NCA architectures for texture generation, which requires separately trained NCA for each individual texture. In this work, we train a single NCA for the evolution of multiple textures, based on individual examples. Our solution provides texture information in the state of each cell, in the form of an internally coded genomic signal, which enables the NCA to generate the expected texture. Such a neural cellular automaton not only maintains its regenerative capability but also allows for interpolation between learned textures and supports grafting techniques. This demonstrates the ability to edit generated textures and the potential for them to merge and coexist within the same automaton. We also address questions related to the influence of the genomic information and the cost function on the evolution of the NCA.