Corpus ID: 219559283

Low Distortion Block-Resampling with Spatially Stochastic Networks

@article{Hong2020LowDB,
  title={Low Distortion Block-Resampling with Spatially Stochastic Networks},
  author={S. J. Hong and Mart{\'i}n Arjovsky and I. Thompson and Darryl Barnhart},
  journal={ArXiv},
  year={2020},
  volume={abs/2006.05394}
}
  • S. J. Hong, Martín Arjovsky, +1 author Darryl Barnhart
  • Published 2020
  • Computer Science, Mathematics
  • ArXiv
  • We formalize and attack the problem of generating new images from old ones that are as diverse as possible, only allowing them to change without restrictions in certain parts of the image while remaining globally consistent. This encompasses the typical situation found in generative modelling, where we are happy with parts of the generated data, but would like to resample others ("I like this generated castle overall, but this tower looks unrealistic, I would like a new one"). In order to… CONTINUE READING
    1 Citations

    Figures and Tables from this paper

    SMILE: Semantically-guided Multi-attribute Image and Layout Editing
    • PDF

    References

    SHOWING 1-10 OF 38 REFERENCES
    Invertibility of Convolutional Generative Networks from Partial Measurements
    • 20
    • PDF
    A Style-Based Generator Architecture for Generative Adversarial Networks
    • 1,575
    • Highly Influential
    • PDF
    Generative Adversarial Nets
    • 20,807
    • PDF
    High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
    • 1,344
    • PDF
    Seeing What a GAN Cannot Generate
    • 63
    • PDF
    LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
    • 638
    • PDF
    HoloGAN: Unsupervised Learning of 3D Representations From Natural Images
    • 105
    • PDF
    Toward Multimodal Image-to-Image Translation
    • 624
    • PDF
    Analyzing and Improving the Image Quality of StyleGAN
    • 383
    • Highly Influential
    • PDF