Corpus ID: 212414684

Creating High Resolution Images with a Latent Adversarial Generator

@article{Berthelot2020CreatingHR,
  title={Creating High Resolution Images with a Latent Adversarial Generator},
  author={David Berthelot and Peyman Milanfar and Ian J. Goodfellow},
  journal={ArXiv},
  year={2020},
  volume={abs/2003.02365}
}
  • David Berthelot, Peyman Milanfar, Ian J. Goodfellow
  • Published in ArXiv 2020
  • Computer Science, Engineering, Mathematics
  • Generating realistic images is difficult, and many formulations for this task have been proposed recently. If we restrict the task to that of generating a particular class of images, however, the task becomes more tractable. That is to say, instead of generating an arbitrary image as a sample from the manifold of natural images, we propose to sample images from a particular "subspace" of natural images, directed by a low-resolution image from the same subspace. The problem we address, while… CONTINUE READING

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 24 REFERENCES

    Conditional Generative Adversarial Nets

    VIEW 7 EXCERPTS
    HIGHLY INFLUENTIAL

    A Fully Progressive Approach to Single-Image Super-Resolution

    VIEW 2 EXCERPTS

    Esrgan: Enhanced superresolution generative adversarial networks

    • X. Wang, K. Yu, +6 authors X. Tang
    • arXiv preprint arXiv:1809.00219
    • 2018
    VIEW 2 EXCERPTS

    NIMA: Neural Image Assessment

    VIEW 1 EXCERPT

    The Perception-Distortion Tradeoff

    VIEW 1 EXCERPT

    To learn image super-resolution

    • A. Bulat, J. Yang, G. Tzimiropoulos
    • use a gan to learn how to do image degradation first. arXiv preprint arXiv:1807.11458
    • 2018
    VIEW 1 EXCERPT