# Texture Synthesis Using Shallow Convolutional Networks with Random Filters

arXiv: https://arxiv.org/abs/1606.00021 · HTML: https://mlsanity.com/paper/1606.00021/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 May 2016.

## Built on by (most cited first, 4 of 4)

- [StyleTime: Style Transfer for Synthetic Time Series Generation](https://mlsanity.com/paper/2209.11306/) (2022)
- [Environment Transfer for Distributed Systems](https://mlsanity.com/paper/2101.01863/) (2021)
- [On Synthetic Texture Datasets: Challenges, Creation, and Curation](https://mlsanity.com/paper/2409.10297/) (2024)
- [Multispectral Texture Synthesis using RGB Convolutional Neural Networks](https://mlsanity.com/paper/2410.16019/) (2024)

## Abstract (arXiv)

Here we demonstrate that the feature space of random shallow convolutional neural networks (CNNs) can serve as a surprisingly good model of natural textures. Patches from the same texture are consistently classified as being more similar then patches from different textures. Samples synthesized from the model capture spatial correlations on scales much larger then the receptive field size, and sometimes even rival or surpass the perceptual quality of state of the art texture models (but show less variability). The current state of the art in parametric texture synthesis relies on the multi-layer feature space of deep CNNs that were trained on natural images. Our finding suggests that such optimized multi-layer feature spaces are not imperative for texture modeling. Instead, much simpler shallow and convolutional networks can serve as the basis for novel texture synthesis algorithms.