Evolving textures from high level descriptions

Abstract

Evolutionary texture synthesis is used in a prototype tool intended to assist a designer or artist by automatically discovering collections of candidate textures to fit a given stylistic description. The textures used here are small colour images created by procedural texture synthesis. This paper describes four examples of stylistic description. Each is defined by a handwritten fitness function that rates how well a given texture meets this style. Genetic programming uses the fitness function to evolve programs written in a texture synthesis language. This system automatically generates a catalogue of variations on the given theme. A designer could then visually scan through these textures to pick out ones that seem aesthetically interesting. Their procedural 'genetic' representation would allow textures to be further adjusted by interactive evolution. The procedural representation also allows re-rendering textures at arbitrary pixel resolutions and provides a way to store them in a highly compressed form allowing lossless reconstruction.