Accurate Image Super-Resolution Using Very Deep Convolutional Networks

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....

Full description

Saved in:
Bibliographic Details
Published in2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) pp. 1646 - 1654
Main Authors Jiwon Kim, Jung Kwon Lee, Kyoung Mu Lee
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2016
Subjects
Convergence
Convolution
Image reconstruction
Signal resolution
Spatial resolution
Training
Online AccessGet full text

Cover

More Information
Summary: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.
ISSN:1063-6919
DOI:10.1109/CVPR.2016.182