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.
@article{arxiv.1511.04491,
title = {Deeply-Recursive Convolutional Network for Image Super-Resolution},
author = {Jiwon Kim and Jung Kwon Lee and Kyoung Mu Lee},
journal= {arXiv preprint arXiv:1511.04491},
year = {2016}
}