Corpus ID: 16400186

From A to Z: Supervised Transfer of Style and Content Using Deep Neural Network Generators

@article{Upchurch2016FromAT,
  title={From A to Z: Supervised Transfer of Style and Content Using Deep Neural Network Generators},
  author={P. Upchurch and Noah Snavely and K. Bala},
  journal={ArXiv},
  year={2016},
  volume={abs/1603.02003}
}
  • P. Upchurch, Noah Snavely, K. Bala
  • Published 2016
  • Computer Science
  • ArXiv
  • We propose a new neural network architecture for solving single-image analogies - the generation of an entire set of stylistically similar images from just a single input image. Solving this problem requires separating image style from content. Our network is a modified variational autoencoder (VAE) that supports supervised training of single-image analogies and in-network evaluation of outputs with a structured similarity objective that captures pixel covariances. On the challenging task of… CONTINUE READING
    Separating Style and Content for Generalized Style Transfer
    41
    Typeface Completion with Generative Adversarial Networks
    1
    Neural Style Transfer for Characters Synthesis via Stack Network
    Learning typographic style: from discrimination to synthesis
    10
    Perceptual Font Manifold from Generative Model
    1
    A Unified Framework for Generalizable Style Transfer: Style and Content Separation
    3
    Generative Adversarial Networks with Inverse Transformation Unit

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 37 REFERENCES
    Deep Visual Analogy-Making
    178
    Visalogy: Answering Visual Analogy Questions
    22
    Deep Convolutional Inverse Graphics Network
    653
    A Neural Algorithm of Artistic Style
    1224
    Convolutional Learning of Spatio-temporal Features
    524
    Unsupervised Learning of Image Transformations
    197
    Generative Adversarial Nets
    17094
    Modeling pixel means and covariances using factorized third-order boltzmann machines
    246
    Generating more realistic images using gated MRF's
    71
    Unsupervised Domain Adaptation by Backpropagation
    1628