Deeply-Recursive Convolutional Network for Image Super-Resolution

Jiwon Kim; Jung Kwon Lee; Kyoung Mu Lee

CVPR 2016oral3548 citations

Deeply-Recursive Convolutional Network for Image Super-Resolution

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.

BibTeX

@inproceedings{cvpr2016_deeplyrecursivec,
  title = {Deeply-Recursive Convolutional Network for Image Super-Resolution},
  author = {Jiwon Kim and Jung Kwon Lee and Kyoung Mu Lee},
  booktitle = {CVPR 2016},
  year = {2016}
}