Corpus ID: 221534501

Deep Cyclic Generative Adversarial Residual Convolutional Networks for Real Image Super-Resolution

@article{Umer2020DeepCG,
  title={Deep Cyclic Generative Adversarial Residual Convolutional Networks for Real Image Super-Resolution},
  author={Rao Muhammad Umer and C. Micheloni},
  journal={ArXiv},
  year={2020},
  volume={abs/2009.03693}
}
  • Rao Muhammad Umer, C. Micheloni
  • Published 2020
  • Computer Science, Engineering
  • ArXiv
  • Recent deep learning based single image super-resolution (SISR) methods mostly train their models in a clean data domain where the low-resolution (LR) and the high-resolution (HR) images come from noise-free settings (same domain) due to the bicubic down-sampling assumption. However, such degradation process is not available in real-world settings. We consider a deep cyclic network structure to maintain the domain consistency between the LR and HR data distributions, which is inspired by the… CONTINUE READING
    1 Citations

    Figures and Tables from this paper

    AIM 2020 Challenge on Real Image Super-Resolution: Methods and Results
    • 11
    • PDF

    References

    SHOWING 1-10 OF 30 REFERENCES
    Deep Generative Adversarial Residual Convolutional Networks for Real-World Super-Resolution
    • 6
    • PDF
    Unsupervised Image Super-Resolution Using Cycle-in-Cycle Generative Adversarial Networks
    • 115
    • PDF
    Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
    • C. Ledig, L. Theis, +6 authors W. Shi
    • Computer Science, Mathematics
    • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
    • 2017
    • 4,259
    • PDF
    ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
    • 610
    • Highly Influential
    • PDF
    Deep Super-Resolution Network for Single Image Super-Resolution with Realistic Degradations
    • 3
    • PDF
    Learning a Single Convolutional Super-Resolution Network for Multiple Degradations
    • 279
    • PDF
    Frequency Separation for Real-World Super-Resolution
    • 23
    • Highly Influential
    • PDF
    Feedback Network for Image Super-Resolution
    • 152
    • PDF
    Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networks
    • 728
    • PDF
    Enhanced Deep Residual Networks for Single Image Super-Resolution
    • 1,572
    • Highly Influential
    • PDF