Image Super-Resolution via Progressive Cascading Residual Network

Namhyuk Ahn, Byungkon Kang, Kyung-Ah Sohn

CVPRW 2018 pp. 791-799

doi:10.1109/CVPRW.2018.00123 /cvprw/2018/ahn2018cvprw-image/

Abstract

The problem of enhancing the resolution of a single low-resolution image has been popularly addressed by recent deep learning techniques. However, many deep learning approaches still fail to deal with extreme super-resolution scenarios because of the instability of training. In this paper, we address this issue by adapting a progressive learning scheme to the deep convolutional neural network. In detail, the overall training proceeds in multiple stages so that the model gradually increases the output image resolution. In our experiments, we show that this property yields a large performance gain compared to the non-progressive learning methods.

CVPRW Semantic Scholar

Cite

Text

Ahn et al. "Image Super-Resolution via Progressive Cascading Residual Network." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2018. doi:10.1109/CVPRW.2018.00123

Markdown

[Ahn et al. "Image Super-Resolution via Progressive Cascading Residual Network." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2018.](https://mlanthology.org/cvprw/2018/ahn2018cvprw-image/) doi:10.1109/CVPRW.2018.00123

BibTeX

@inproceedings{ahn2018cvprw-image,
  title     = {{Image Super-Resolution via Progressive Cascading Residual Network}},
  author    = {Ahn, Namhyuk and Kang, Byungkon and Sohn, Kyung-Ah},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2018},
  pages     = {791-799},
  doi       = {10.1109/CVPRW.2018.00123},
  url       = {https://mlanthology.org/cvprw/2018/ahn2018cvprw-image/}
}