Texture Enhancement via High-Resolution Style Transfer for Single-Image Super-Resolution

@article{Ahn2016TextureEV,
  title={Texture Enhancement via High-Resolution Style Transfer for Single-Image Super-Resolution},
  author={Il Jun Ahn and Woo Hyun Nam},
  journal={ArXiv},
  year={2016},
  volume={abs/1612.00085}
}
  • Il Jun Ahn, Woo Hyun Nam
  • Published 2016
  • Computer Science, Materials Science
  • ArXiv
  • Recently, various deep-neural-network (DNN)-based approaches have been proposed for single-image super-resolution (SISR). Despite their promising results on major structure regions such as edges and lines, they still suffer from limited performance on texture regions that consist of very complex and fine patterns. This is because, during the acquisition of a low-resolution (LR) image via down-sampling, these regions lose most of the high frequency information necessary to represent the texture… CONTINUE READING

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 29 REFERENCES
    Image Super-Resolution Using Deep Convolutional Networks
    2893
    Super-resolution through neighbor embedding
    1163
    Image Style Transfer Using Convolutional Neural Networks
    1890
    Super-resolution from a single image
    1457
    Learning a Deep Convolutional Network for Image Super-Resolution
    2109
    Perceptual Losses for Real-Time Style Transfer and Super-Resolution
    3329