# Learning Texture Manifolds with the Periodic Spatial GAN

arXiv: https://arxiv.org/abs/1705.06566 · HTML: https://mlsanity.com/paper/1705.06566/

## Key facts

- Cited by 53 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 May 2017.

## Built on by (most cited first, 30 of 53)

- [Aligning Latent and Image Spaces to Connect the Unconnectable](https://mlsanity.com/paper/2104.06954/) (2021)
- [InfinityGAN: Towards Infinite-Pixel Image Synthesis](https://mlsanity.com/paper/2104.03963/) (2021)
- [Drop the GAN: In Defense of Patches Nearest Neighbors as Single Image Generative Models](https://mlsanity.com/paper/2103.15545/) (2021)
- [Generative Modelling of BRDF Textures from Flash Images](https://mlsanity.com/paper/2102.11861/) (2021)
- [Material Palette: Extraction of Materials from a Single Image](https://mlsanity.com/paper/2311.17060/) (2023)
- [TileGen: Tileable, Controllable Material Generation and Capture](https://mlsanity.com/paper/2206.05649/) (2022)
- [Solving Inverse Problems by Joint Posterior Maximization with Autoencoding Prior](https://mlsanity.com/paper/2103.01648/) (2021)
- [SeamlessGAN: Self-Supervised Synthesis of Tileable Texture Maps](https://mlsanity.com/paper/2201.05120/) (2022)
- [SinIR: Efficient General Image Manipulation with Single Image Reconstruction](https://mlsanity.com/paper/2106.07140/) (2021)
- [Diverse Generation from a Single Video Made Possible](https://mlsanity.com/paper/2109.08591/) (2021)
- [Generative Adversarial Networks for Image Super-Resolution: A Survey](https://mlsanity.com/paper/2204.13620/) (2022)
- [CharacterGAN: Few-Shot Keypoint Character Animation and Reposing](https://mlsanity.com/paper/2102.03141/) (2021)
- [Texture Generation with Neural Cellular Automata](https://mlsanity.com/paper/2105.07299/) (2021)
- [Anything in Any Scene: Photorealistic Video Object Insertion](https://mlsanity.com/paper/2401.17509/) (2024)
- [Generating Novel Scene Compositions from Single Images and Videos](https://mlsanity.com/paper/2103.13389/) (2021)
- [Generating Non-Stationary Textures using Self-Rectification](https://mlsanity.com/paper/2401.02847/) (2024)
- [TexTile: A Differentiable Metric for Texture Tileability](https://mlsanity.com/paper/2403.12961/) (2024)
- [Generative Escher Meshes](https://mlsanity.com/paper/2309.14564/) (2023)
- [Compositional Neural Textures](https://mlsanity.com/paper/2404.12509/) (2024)
- [Infinite Texture: Text-guided High Resolution Diffusion Texture Synthesis](https://mlsanity.com/paper/2405.08210/) (2024)
- [Paying U-Attention to Textures: Multi-Stage Hourglass Vision Transformer for Universal Texture Synthesis](https://mlsanity.com/paper/2202.11703/) (2022)
- [Diffusion-based Holistic Texture Rectification and Synthesis](https://mlsanity.com/paper/2309.14759/) (2023)
- [Towards Universal Texture Synthesis by Combining Texton Broadcasting with Noise Injection in StyleGAN-2](https://mlsanity.com/paper/2203.04221/) (2022)
- [Exemplar-based Pattern Synthesis with Implicit Periodic Field Network](https://mlsanity.com/paper/2204.01671/) (2022)
- [Texture Representation via Analysis and Synthesis with Generative Adversarial Networks](https://mlsanity.com/paper/2212.09983/) (2022)
- [MetaHead: An Engine to Create Realistic Digital Head](https://mlsanity.com/paper/2304.00838/) (2023)
- [Local Padding in Patch-Based GANs for Seamless Infinite-Sized Texture Synthesis](https://mlsanity.com/paper/2309.02340/) (2023)
- [Directional Texture Editing for 3D Models](https://mlsanity.com/paper/2309.14872/) (2023)
- [STS-GAN: Can We Synthesize Solid Texture with High Fidelity from Arbitrary 2D Exemplar?](https://mlsanity.com/paper/2102.03973/) (2021)
- [Diverse Single Image Generation with Controllable Global Structure](https://mlsanity.com/paper/2102.04780/) (2021)

## Abstract (arXiv)

This paper introduces a novel approach to texture synthesis based on generative adversarial networks (GAN) (Goodfellow et al., 2014). We extend the structure of the input noise distribution by constructing tensors with different types of dimensions. We call this technique Periodic Spatial GAN (PSGAN). The PSGAN has several novel abilities which surpass the current state of the art in texture synthesis. First, we can learn multiple textures from datasets of one or more complex large images. Second, we show that the image generation with PSGANs has properties of a texture manifold: we can smoothly interpolate between samples in the structured noise space and generate novel samples, which lie perceptually between the textures of the original dataset. In addition, we can also accurately learn periodical textures. We make multiple experiments which show that PSGANs can flexibly handle diverse texture and image data sources. Our method is highly scalable and it can generate output images of arbitrary large size.