Evolved procedural textures using genetic programming

Evolved procedural textures using genetic programming

Adam Hewgill and Brian J Ross.
"Procedural 3D Texture Synthesis Using Genetic Programming".
Computers and Graphics Journal, vol.28, n.4, 2004, pp.569-584.
Preprint (PDF). Journal web site.

Some examples...

Example A. The following images show procedural textures trained from a model consisting of mountains with white peaks, grey cliffs, and green valley. After extracting sample points from the model, the gradient and blue channels were swapped. The results exhibit a variety of interesting mineral-like effects. The first 2 terrain images in the top row of each solution set are training results. All the solutions use the same experiment parameters, except for different random number seeds.

Solution A1: Amethyst 1

Solution A2: Amethyst 2

Solution A3: Amethyst and Jade

Solution A4: Amethyst and Amber

Solution A5: Opalescent Amethyst

Solution A6: Solarized Ruby

Solution A7: Extraterrestrial


Example B. These images are trained from a blue cube with coloured 'ribbons' around each orthogonal direction. Vertex normals are shared (interpolated for surrounding faces). This will give a warping effect to results.

Solution B1:

Solution B2:

Solution B3:

Solution B4:

Solution B5:

Solution B6:

Solution B7:

Back to home page.