We propose a generative model of 2D and 3D natural textures with diversity, visual fidelity and at high computational efficiency. This is enabled by a family of methods that extend ideas from classic stochastic procedural texturing (Perlin noise) to learned, deep, non-linearities. The key idea is a hard-coded, tunable and differentiable step that feeds multiple transformed random 2D or 3D fields into an MLP that can be sampled over infinite domains. Our model encodes all exemplars from a diverse set of textures without a need to be re-trained for each exemplar. Applications include texture interpolation, and learning 3D textures from 2D exemplars.
@article{arxiv.1912.04158,
title = {Learning a Neural 3D Texture Space from 2D Exemplars},
author = {Philipp Henzler and Niloy J. Mitra and Tobias Ritschel},
journal= {arXiv preprint arXiv:1912.04158},
year = {2020}
}