mlsanityData to 7 Oct 2026

A geometrically aware auto-encoder for multi-texture synthesis

arXiv 2302.01616 ↗First posted 3 Feb 2023cs.CV cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

We propose an auto-encoder architecture for multi-texture synthesis. The approach relies on both a compact encoder accounting for second order neural statistics and a generator incorporating adaptive periodic content. Images are embedded in a compact and geometrically consistent latent space, where the texture representation and its spatial organisation are disentangled. Texture synthesis and interpolation tasks can be performed directly from these latent codes. Our experiments demonstrate that our model outperforms state-of-the-art feed-forward methods in terms of visual quality and various texture related metrics.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 18 of its 21 references that are in the map. First posted on arXiv 3 Feb 2023.

Builds on

18 of 21 references.

References · 18

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  2. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  3. 2017Improved Training of Wasserstein GANscited by 2,223
  4. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
  5. 2017Universal Style Transfer via Feature Transformscited by 352
  6. 2019SinGAN: Learning a Generative Model from a Single Natural Imagecited by 348
  7. 2016Texture Networks: Feed-forward Synthesis of Textures and Stylized Imagescited by 173
  8. 2017Learning Texture Manifolds with the Periodic Spatial GANcited by 53
  9. 2019Learning a Neural 3D Texture Space from 2D Exemplarscited by 53
  10. 2016Texture Synthesis with Spatial Generative Adversarial Networkscited by 45
  11. 2019Texture Mixer: A Network for Controllable Synthesis and Interpolation of Texturecited by 14
  12. 2015Texture Synthesis Using Convolutional Neural Networkscited by 8
6 more
  1. 2020Transposer: Universal Texture Synthesis Using Feature Maps as Transposed Convolution Filtercited by 8
  2. 2017Second-order Convolutional Neural Networkscited by 7
  3. 2020High resolution neural texture synthesis with long range constraintscited by 6
  4. 2022Paying U-Attention to Textures: Multi-Stage Hourglass Vision Transformer for Universal Texture Synthesiscited by 4
  5. 2022Towards Universal Texture Synthesis by Combining Texton Broadcasting with Noise Injection in StyleGAN-2cited by 3
  6. 2019User-Controllable Multi-Texture Synthesis with Generative Adversarial Networkscited by 1

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024Multispectral Texture Synthesis using RGB Convolutional Neural Networkscited by 0