Timezone: »

Texture Synthesis Using Convolutional Neural Networks
Leon A Gatys · Alexander Ecker · Matthias Bethge

Mon Dec 07 04:00 PM -- 08:59 PM (PST) @ 210 C #1

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.

Author Information

Leon A Gatys (University of Tübingen)
Alexander Ecker (University of Tuebingen)
Matthias Bethge (CIN, University Tübingen)

More from the Same Authors