Texture Synthesis Using Convolutional Neural Networks

Leon A. Gatys, Alexander S. Ecker, Matthias Bethge
5/27/2015
cs.CVcs.NEq-bio.NC

Official code: leongatys/DeepTextures (275 stars, last commit 2016-03-07).

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.

View on arXivView PDF

Code Implementations(1)

leongatys/DeepTexturesOfficial100%

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

27582Python, Jupyter NotebookOct 20, 201510 years ago

Similar Papers

Perceptual misalignment of texture representations in convolutional neural networks

88% match2026

Texture Representations in Deep Vision Models: Comparing CNNs, Vision Transformers, and Human Perception

87% match2026

Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networks

84% match1 repo2912016

Mechanism of feature learning in convolutional neural networks

84% match1 repo112023

Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform

83% match1 repo5762018

Learning Robust Global Representations by Penalizing Local Predictive Power

83% match2 repos182019

Cite this paper

@article{gatys2015texture,
  title  = {Texture Synthesis Using Convolutional Neural Networks},
  author = {Leon A. Gatys and Alexander S. Ecker and Matthias Bethge},
  year   = {2015},
  eprint = {1505.07376},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1505.07376}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1505.07376.svg)](https://codeofpaper.com/paper/1505.07376)

Discussion