• Computer Science
  • Published in ICML 2016

Texture Networks: Feed-forward Synthesis of Textures and Stylized Images

@inproceedings{Ulyanov2016TextureNF,
  title={Texture Networks: Feed-forward Synthesis of Textures and Stylized Images},
  author={Dmitry Ulyanov and Vadim Lebedev and Andrea Vedaldi and Victor S. Lempitsky},
  booktitle={ICML},
  year={2016}
}
Gatys et al. recently demonstrated that deep networks can generate beautiful textures and stylized images from a single texture example. However, their methods require a slow and memory-consuming optimization process. We propose here an alternative approach that moves the computational burden to a learning stage. Given a single example of a texture, our approach trains compact feed-forward convolutional networks to generate multiple samples of the same texture of arbitrary size and to transfer… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 365 CITATIONS

Identity-Preserving Face Recovery from Stylized Portraits

VIEW 11 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

A Fast Multi-layer Approximation to Semi-discrete Optimal Transport

VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Increasing Image Memorability with Neural Style Transfer

VIEW 10 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Material Synthesis Techniques from a Data-driven Perspective

VIEW 7 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Recovering Faces From Portraits with Auxiliary Facial Attributes

VIEW 7 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Non-stationary texture synthesis by adversarial expansion

VIEW 5 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Recent Advances in Deep Learning: An Overview

VIEW 5 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Style Transfer at 100+ FPS Via Sub-Pixel Super-Resolution

VIEW 7 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Diversified Texture Synthesis with Feed-Forward Networks

VIEW 8 EXCERPTS
CITES BACKGROUND, METHODS & RESULTS
HIGHLY INFLUENCED

Improved Texture Networks: Maximizing Quality and Diversity in Feed-Forward Stylization and Texture Synthesis

VIEW 10 EXCERPTS
CITES METHODS & BACKGROUND

FILTER CITATIONS BY YEAR

2016
2020

CITATION STATISTICS

  • 49 Highly Influenced Citations

  • Averaged 110 Citations per year from 2017 through 2019

References

Publications referenced by this paper.
SHOWING 1-10 OF 17 REFERENCES

A Neural Algorithm of Artistic Style

VIEW 26 EXCERPTS
HIGHLY INFLUENTIAL

Return of the devil in the details: Delving deep into convolutional nets

  • Chatfield, Ken, +5 authors Andrew
  • arXiv preprint arXiv:1405.3531,
  • 2014
VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

A Parametric Texture Model Based on Joint Statistics of Complex Wavelet Coefficients

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Generative Moment Matching Networks

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Generative Adversarial Nets

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL