mlsanityData to 7 Oct 2026

Texture Synthesis with Spatial Generative Adversarial Networks

arXiv 1611.08207 ↗First posted 24 Nov 2016cs.CV stat.MLcited by 45

Not on the map. Why?

Abstract (arXiv)

Generative adversarial networks (GANs) are a recent approach to train generative models of data, which have been shown to work particularly well on image data. In the current paper we introduce a new model for texture synthesis based on GAN learning. By extending the input noise distribution space from a single vector to a whole spatial tensor, we create an architecture with properties well suited to the task of texture synthesis, which we call spatial GAN (SGAN). To our knowledge, this is the first successful completely data-driven texture synthesis method based on GANs. Our method has the following features which make it a state of the art algorithm for texture synthesis: high image quality of the generated textures, very high scalability w.r.t. the output texture size, fast real-time forward generation, the ability to fuse multiple diverse source images in complex textures. To illustrate these capabilities we present multiple experiments with different classes of texture images and use cases. We also discuss some limitations of our method with respect to the types of texture images it can synthesize, and compare it to other neural techniques for texture generation.

Key facts. Cited by 45 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 Nov 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 14; 2022: 11; 2023: 9; 2024: 8; 2025: 2; 2026: 1.

45 papers.

Sort:

By area:

  1. 2022Generative Adversarial Networkscited by 5,603
  2. 2021Aligning Latent and Image Spaces to Connect the Unconnectablecited by 70
  3. 2021Drop the GAN: In Defense of Patches Nearest Neighbors as Single Image Generative Modelscited by 51
  4. 2023Autoregressive Conditional Neural Processescited by 32
  5. 2022SeamlessGAN: Self-Supervised Synthesis of Tileable Texture Mapscited by 19
  6. 2022Astronomia ex machina: a history, primer, and outlook on neural networks in astronomycited by 17
  7. 2021Generative Adversarial Networks: A Survey Towards Private and Secure Applicationscited by 15
  8. 2022PetsGAN: Rethinking Priors for Single Image Generationcited by 14
  9. 2021SinIR: Efficient General Image Manipulation with Single Image Reconstructioncited by 13
  10. 2021Diverse Generation from a Single Video Made Possiblecited by 13
  11. 2021Generative Adversarial Networks (GANs) in Networking: A Comprehensive Survey & Evaluationcited by 11
  12. 2022Generative Adversarial Networks for Image Super-Resolution: A Surveycited by 11
33 more
  1. 2021CharacterGAN: Few-Shot Keypoint Character Animation and Reposingcited by 9
  2. 2024Anything in Any Scene: Photorealistic Video Object Insertioncited by 9
  3. 2021Generating Novel Scene Compositions from Single Images and Videoscited by 8
  4. 2024Generating Non-Stationary Textures using Self-Rectificationcited by 8
  5. 2024VCD-Texture: Variance Alignment based 3D-2D Co-Denoising for Text-Guided Texturingcited by 8
  6. 2024Infinite Texture: Text-guided High Resolution Diffusion Texture Synthesiscited by 5
  7. 2022Paying U-Attention to Textures: Multi-Stage Hourglass Vision Transformer for Universal Texture Synthesiscited by 4
  8. 2022Learning Continuous Implicit Representation for Near-Periodic Patternscited by 4
  9. 2023Diffusion-based Holistic Texture Rectification and Synthesiscited by 4
  10. 2022Towards Universal Texture Synthesis by Combining Texton Broadcasting with Noise Injection in StyleGAN-2cited by 3
  11. 2022Exemplar-based Pattern Synthesis with Implicit Periodic Field Networkcited by 3
  12. 2022Texture Representation via Analysis and Synthesis with Generative Adversarial Networkscited by 3
  13. 2023Local Padding in Patch-Based GANs for Seamless Infinite-Sized Texture Synthesiscited by 3
  14. 2021Diverse Single Image Generation with Controllable Global Structurecited by 2
  15. 2022BlendGAN: Learning and Blending the Internal Distributions of Single Images by Spatial Image-Identity Conditioningcited by 2
  16. 2023A stable deep adversarial learning approach for geological facies generationcited by 2
  17. 2023Prediction of Transportation Index for Urban Patterns in Small and Medium-sized Indian Cities using Hybrid RidgeGAN Modelcited by 2
  18. 2024SYNOSIS: Image synthesis pipeline for machine vision in metal surface inspectioncited by 2
  19. 2021SETGAN: Scale and Energy Trade-off GANs for Image Applications on Mobile Platformscited by 1
  20. 2021Texture synthesis via projection onto multiscale, multilayer statisticscited by 1
  21. 2021Generative Adversarial Networks for Astronomical Images Generationcited by 1
  22. 2023A geometrically aware auto-encoder for multi-texture synthesiscited by 1
  23. 2023Learning in a Single Domain for Non-Stationary Multi-Texture Synthesiscited by 1
  24. 2023Bayesian tomography using polynomial chaos expansion and deep generative networkscited by 1
  25. 2024Towards Practical Single-shot Motion Synthesiscited by 1
  26. 2024NeRF-Texture: Synthesizing Neural Radiance Field Texturescited by 1
  27. 2021Image Shape Manipulation from a Single Augmented Training Samplecited by 0
  28. 2021Learning Spatially-Adaptive Squeeze-Excitation Networks for Image Synthesis and Image Recognitioncited by 0
  29. 2023Redes Generativas Adversarias (GAN) Fundamentos Te'oricos y Aplicacionescited by 0
  30. 2024Multispectral Texture Synthesis using RGB Convolutional Neural Networkscited by 0
  31. 2025By-Example Synthesis of Vector Texturescited by 0
  32. 2025Texture Image Synthesis Using Spatial GAN Based on Vision Transformerscited by 0
  33. 2026To GAN or Not To GAN: Segmentation Analysis on Mars DEMcited by 0