Deeply-Recursive Convolutional Network for Image Super-Resolution

Jiwon Kim, Jung Kwon Lee, Kyoung Mu Lee; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 1637-1645

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.

Related Material


[pdf]
[bibtex]
@InProceedings{Kim_2016_CVPR,
author = {Kim, Jiwon and Kwon Lee, Jung and Mu Lee, Kyoung},
title = {Deeply-Recursive Convolutional Network for Image Super-Resolution},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2016}
}