# Texture Synthesis Using Convolutional Neural Networks

arXiv: https://arxiv.org/abs/1505.07376 · HTML: https://mlsanity.com/paper/1505.07376/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 May 2015.

## Built on by (most cited first, 8 of 8)

- [Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges](https://mlsanity.com/paper/2104.13478/) (2021)
- [Pre-trained Trojan Attacks for Visual Recognition](https://mlsanity.com/paper/2312.15172/) (2023)
- [Degrade is Upgrade: Learning Degradation for Low-light Image Enhancement](https://mlsanity.com/paper/2103.10621/) (2021)
- [A Brief Introduction to Generative Models](https://mlsanity.com/paper/2103.00265/) (2021)
- [A geometrically aware auto-encoder for multi-texture synthesis](https://mlsanity.com/paper/2302.01616/) (2023)
- [Non-Parametric Neural Style Transfer](https://mlsanity.com/paper/2108.12847/) (2021)
- [Semantic Image Fusion](https://mlsanity.com/paper/2110.06697/) (2021)
- [Image Steganography based on Style Transfer](https://mlsanity.com/paper/2203.04500/) (2022)

## Abstract (arXiv)

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.