Texture Synthesis Using Convolutional Neural Networks
Abstract
Here we introduce a new model of natural textures based on the feature spaces of convolutional neural networks optimised for object recognition. Samples from the model are of high perceptual quality demonstrating the generative power of neural networks trained in a purely discriminative fashion. Within the model, textures are represented by the correlations between feature maps in several layers of the network. We show that across layers the texture representations increasingly capture the statistical properties of natural images while making object information more and more explicit. The model provides a new tool to generate stimuli for neuroscience and might offer insights into the deep representations learned by convolutional neural networks.
Cite
@article{arxiv.1505.07376,
title = {Texture Synthesis Using Convolutional Neural Networks},
author = {Leon A. Gatys and Alexander S. Ecker and Matthias Bethge},
journal= {arXiv preprint arXiv:1505.07376},
year = {2015}
}
Comments
Revision for NIPS 2015 Camera Ready. In line with reviewer's comments we now focus on the texture model and texture synthesis performance. We limit the relationship of our texture model to the ventral stream and its potential use for neuroscience to the discussion of the paper