mlsanityData to 13 Oct 2026

Towards Universal Texture Synthesis by Combining Texton Broadcasting with Noise Injection in StyleGAN-2

arXiv 2203.04221 ↗First posted 8 Mar 2022cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

We present a new approach for universal texture synthesis by incorporating a multi-scale texton broadcasting module in the StyleGAN-2 framework. The texton broadcasting module introduces an inductive bias, enabling generation of broader range of textures, from those with regular structures to completely stochastic ones. To train and evaluate the proposed approach, we construct a comprehensive high-resolution dataset that captures the diversity of natural textures as well as stochastic variations within each perceptually uniform texture. Experimental results demonstrate that the proposed approach yields significantly better quality textures than the state of the art. The ultimate goal of this work is a comprehensive understanding of texture space.

Key facts. Cited by 3 papers in the map (data through 13 Oct 2026). Builds on 38 of its 68 references that are in the map. First posted on arXiv 8 Mar 2022.

Builds on

38 of 68 references.

References · 38

  1. 2017Attention Is All You Needcited by 60,106
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,950
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,321
  4. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,000
  5. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,516
  6. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,585
  7. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,687
  8. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,686
  9. 2017Improved Training of Wasserstein GANscited by 2,226
  10. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,225
  11. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,183
  12. 2013Describing Textures in the Wildcited by 2,115
26 more
  1. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,039
  2. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,906
  3. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,621
  4. 2021Alias-Free Generative Adversarial Networkscited by 1,183
  5. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  6. 2019Interpreting the Latent Space of GANs for Semantic Face Editingcited by 692
  7. 2019Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?cited by 675
  8. 2017Convolutional Sequence to Sequence Learningcited by 552
  9. 2020InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANscited by 393
  10. 2017Improved Texture Networks: Maximizing Quality and Diversity in Feed-forward Stylization and Texture Synthesiscited by 215
  11. 2019Texture Fields: Learning Texture Representations in Function Spacecited by 210
  12. 2016Texture Networks: Feed-forward Synthesis of Textures and Stylized Imagescited by 173
  13. 2020Adversarial Generation of Continuous Imagescited by 135
  14. 2020Image Generators with Conditionally-Independent Pixel Synthesiscited by 106
  15. 2014Material Recognition in the Wild with the Materials in Context Databasecited by 78
  16. 2020Positional Encoding as Spatial Inductive Bias in GANscited by 69
  17. 2017Diversified Texture Synthesis with Feed-forward Networkscited by 59
  18. 2017Learning Texture Manifolds with the Periodic Spatial GANcited by 53
  19. 2019Learning a Neural 3D Texture Space from 2D Exemplarscited by 53
  20. 2016Texture Synthesis with Spatial Generative Adversarial Networkscited by 45
  21. 2015Deep filter banks for texture recognition, description, and segmentationcited by 19
  22. 2020GramGAN: Deep 3D Texture Synthesis From 2D Exemplarscited by 18
  23. 2021Toward Spatially Unbiased Generative Modelscited by 17
  24. 2019Progressive Augmentation of GANscited by 13
  25. 2020Differential Viewpoints for Ground Terrain Material Recognitioncited by 8
  26. 2019Conditional Generative ConvNets for Exemplar-based Texture Synthesiscited by 3

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 2.

3 papers.

  1. 2023A geometrically aware auto-encoder for multi-texture synthesiscited by 1
  2. 2024Diffusion-based image inpainting with internal learningcited by 1
  3. 2024Multispectral Texture Synthesis using RGB Convolutional Neural Networkscited by 0