Deeply-Recursive Convolutional Network for Image Super-Resolution

CVPR 2016

doi:10.1109/CVPR.2016.181 /cvpr/2016/kim2016cvpr-deeplyrecursive/

Abstract

We propose an image super-resolution method (SR) using a deeply-recursive convolutional network (DRCN). Our network has a very deep recursive layer (up to 16 recursions). Increasing recursion depth can improve performance without introducing new parameters for additional convolutions. Albeit advantages, learning a DRCN is very hard with a standard gradient descent method due to exploding/ vanishing gradients. To ease the difficulty of training, we propose two extensions: recursive supervision and skip-connection. Our method outperforms previous methods by a large margin.

PDF CVPR Semantic Scholar

Cite

Text

Kim et al. "Deeply-Recursive Convolutional Network for Image Super-Resolution." Conference on Computer Vision and Pattern Recognition, 2016. doi:10.1109/CVPR.2016.181

Markdown

[Kim et al. "Deeply-Recursive Convolutional Network for Image Super-Resolution." Conference on Computer Vision and Pattern Recognition, 2016.](https://mlanthology.org/cvpr/2016/kim2016cvpr-deeplyrecursive/) doi:10.1109/CVPR.2016.181

BibTeX

@inproceedings{kim2016cvpr-deeplyrecursive,
  title     = {{Deeply-Recursive Convolutional Network for Image Super-Resolution}},
  author    = {Kim, Jiwon and Lee, Jung Kwon and Lee, Kyoung Mu},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2016},
  doi       = {10.1109/CVPR.2016.181},
  url       = {https://mlanthology.org/cvpr/2016/kim2016cvpr-deeplyrecursive/}
}