Texture Synthesis Using Convolutional Neural Networks

by   Leon A. Gatys, et al.

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.


page 5

page 6


Synthesising Dynamic Textures using Convolutional Neural Networks

Here we present a parametric model for dynamic textures. The model is ba...

Texture Synthesis Using Shallow Convolutional Networks with Random Filters

Here we demonstrate that the feature space of random shallow convolution...

A Powerful Generative Model Using Random Weights for the Deep Image Representation

To what extent is the success of deep visualization due to the training?...

Texture synthesis via projection onto multiscale, multilayer statistics

We provide a new model for texture synthesis based on a multiscale, mult...

Sound texture synthesis using RI spectrograms

This article introduces a new parametric synthesis method for sound text...

Passing Multi-Channel Material Textures to a 3-Channel Loss

Our objective is to compute a textural loss that can be used to train te...

GANosaic: Mosaic Creation with Generative Texture Manifolds

This paper presents a novel framework for generating texture mosaics wit...

Code Repositories


Code to synthesise textures using convolutional neural networks as described in Gatys et al. 2015 (http://arxiv.org/abs/1505.07376)

view repo


Undergraduate Research Project (Jan. 2016)

view repo


Tensorflow implementation of texture synthesis. (Gatys et al., 2015 https://arxiv.org/abs/1505.07376)

view repo

Please sign up or login with your details

Forgot password? Click here to reset