Accurate Image Super-Resolution Using Very Deep Convolutional Networks
Authors:
- Jiwon KimJKJiwon Kim
- Jung Kwon LeeJLJung Kwon Lee
- Kyoung Mu LeeKLKyoung Mu Lee
Top Cited Papers
- 1 June 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 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.Keywords
All Related Versions
This publication has 20 references indexed in Scilit:
- Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification2015
- Fast and accurate image upscaling with super-resolution forests2015
- Anchored Neighborhood Regression for Fast Example-Based Super-Resolution2013
- Fast Direct Super-Resolution by Simple Functions2013
- Super-resolution using neighbor embedding of back-projection residuals2013
- On Single Image Scale-Up Using Sparse-Representations2012
- Super-resolution through neighbor embedding2004
- A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics2002
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- Improving resolution by image registrationCVGIP: Graphical Models and Image Processing, 1991