Corpus ID: 16728483

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

@inproceedings{Ulyanov2016TextureNF,
  title={Texture Networks: Feed-forward Synthesis of Textures and Stylized Images},
  author={D. Ulyanov and V. Lebedev and A. Vedaldi and V. Lempitsky},
  booktitle={ICML},
  year={2016}
}
  • D. Ulyanov, V. Lebedev, +1 author V. Lempitsky
  • Published in ICML 2016
  • Computer Science
  • 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
    495 Citations
    Improved Texture Networks: Maximizing Quality and Diversity in Feed-Forward Stylization and Texture Synthesis
    • 293
    • PDF
    Texture Attribute Synthesis and Transfer Using Feed-Forward CNNs
    • 2
    • PDF
    Diversified Texture Synthesis with Feed-Forward Networks
    • 120
    • Highly Influenced
    • PDF
    Fast Texture Synthesis via Pseudo Optimizer
    • W. Shi, Yu Qiao
    • Computer Science
    • 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
    • 2020
    • 2
    • Highly Influenced
    • PDF
    TextureGAN: Controlling Deep Image Synthesis with Texture Patches
    • 125
    • PDF
    GramGAN: Deep 3D Texture Synthesis From 2D Exemplars
    Multimodal Transfer: A Hierarchical Deep Convolutional Neural Network for Fast Artistic Style Transfer
    • 77
    • Highly Influenced
    • PDF
    Two-Stream Convolutional Networks for Dynamic Texture Synthesis
    • 25
    • PDF
    Stable and Controllable Neural Texture Synthesis and Style Transfer Using Histogram Losses
    • 106
    • PDF

    References

    SHOWING 1-10 OF 20 REFERENCES
    A Neural Algorithm of Artistic Style
    • 1,316
    • Highly Influential
    • PDF
    Understanding deep image representations by inverting them
    • 1,127
    • PDF
    Return of the Devil in the Details: Delving Deep into Convolutional Nets
    • 2,667
    • PDF
    Learning to generate chairs with convolutional neural networks
    • 564
    • PDF
    Very Deep Convolutional Networks for Large-Scale Image Recognition
    • 41,521
    • Highly Influential
    • PDF
    Generative Moment Matching Networks
    • 494
    • Highly Influential
    • PDF
    Fully Convolutional Networks for Semantic Segmentation
    • 7,847
    • PDF
    Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
    • 6,886
    • Highly Influential
    • PDF