# A survey of exemplar-based texture synthesis

arXiv: https://arxiv.org/abs/1707.07184 · HTML: https://mlsanity.com/paper/1707.07184/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Jul 2017.

## Built on by (most cited first, 13 of 13)

- [SeamlessGAN: Self-Supervised Synthesis of Tileable Texture Maps](https://mlsanity.com/paper/2201.05120/) (2022)
- [Generalized Rectifier Wavelet Covariance Models For Texture Synthesis](https://mlsanity.com/paper/2203.07902/) (2022)
- [Generative Escher Meshes](https://mlsanity.com/paper/2309.14564/) (2023)
- [Paying U-Attention to Textures: Multi-Stage Hourglass Vision Transformer for Universal Texture Synthesis](https://mlsanity.com/paper/2202.11703/) (2022)
- [Stochastic Geometry Models for Texture Synthesis of Machined Metallic Surfaces: Sandblasting and Milling](https://mlsanity.com/paper/2403.13439/) (2024)
- [One Noise to Rule Them All: Learning a Unified Model of Spatially-Varying Noise Patterns](https://mlsanity.com/paper/2404.16292/) (2024)
- [SYNOSIS: Image synthesis pipeline for machine vision in metal surface inspection](https://mlsanity.com/paper/2410.14844/) (2024)
- [NeRF synthesis with shading guidance](https://mlsanity.com/paper/2306.11556/) (2023)
- [ARTEMIS: Using GANs with Multiple Discriminators to Generate Art](https://mlsanity.com/paper/2311.08278/) (2023)
- [Multi-Texture Synthesis through Signal Responsive Neural Cellular Automata](https://mlsanity.com/paper/2407.05991/) (2024)
- [SciTextures: Collecting and Connecting Visual Patterns, Models, and Code Across Science and Art](https://mlsanity.com/paper/2511.01817/) (2025)
- [Texture Edge detection by Patch consensus (TEP)](https://mlsanity.com/paper/2403.11038/) (2024)
- [Advances in Neural 3D Mesh Texturing: A Survey](https://mlsanity.com/paper/2606.00137/) (2026)

## Abstract (arXiv)

Exemplar-based texture synthesis is the process of generating, from an input sample, new texture images of arbitrary size and which are perceptually equivalent to the sample. The two main approaches are statistics-based methods and patch re-arrangement methods. In the first class, a texture is characterized by a statistical signature; then, a random sampling conditioned to this signature produces genuinely different texture images. The second class boils down to a clever "copy-paste" procedure, which stitches together large regions of the sample. Hybrid methods try to combine ideas from both approaches to avoid their hurdles. The recent approaches using convolutional neural networks fit to this classification, some being statistical and others performing patch re-arrangement in the feature space. They produce impressive synthesis on various kinds of textures. Nevertheless, we found that most real textures are organized at multiple scales, with global structures revealed at coarse scales and highly varying details at finer ones. Thus, when confronted with large natural images of textures the results of state-of-the-art methods degrade rapidly, and the problem of modeling them remains wide open.