Accurate Image Super-Resolution Using Very Deep Convolutional Networks

Jiwon Kim, Jung Kwon Lee, Kyoung Mu Lee; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 1646-1654

Abstract


We present a highly accurate single image superresolution (SR) method. Our method uses a very deep convolutional network inspired by VGG-net used for ImageNet classification [19]. We find increasing our network depth shows a significant improvement in accuracy. Our final model uses 20 weight layers. By cascading small filters many times in a deep network structure, contextual information over large image regions is exploited in an efficient way. With very deep networks, however, convergence speed becomes a critical issue during training. We propose a simple yet effective training procedure. We learn residuals only and use extremely high learning rates (104 times higher than SRCNN [6]) enabled by adjustable gradient clipping. Our proposed method performs better than existing methods in accuracy and visual improvements in our results are easily noticeable.

Related Material


[pdf] [video]
[bibtex]
@InProceedings{Kim_2016_CVPR,
author = {Kim, Jiwon and Lee, Jung Kwon and Lee, Kyoung Mu},
title = {Accurate Image Super-Resolution Using Very Deep Convolutional Networks},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2016}
}