Single image super-resolution based on deep learning and gradient transformation
Authors:
- Jingxu ChenJCJingxu Chen
- Xiaohai HeXHXiaohai He
- Honggang ChenHCHonggang Chen
- Qizhi TengQTQizhi Teng
- Linbo QingLQLinbo Qing
- 1 November 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 663-667
Abstract
In this paper, an effective single image super-resolution method based on deep learning and gradient transformation is proposed. Firstly, the low-resolution image is upscaled by convolutional neural network. Then we calculate the gradients of the upscaled image, and transform them into desired gradients by using gradient transformation network. The transformed gradients are utilized as a constraint to establish the reconstruction energy function. Finally, we optimize this energy function to estimate the high-resolution image. Experimental results show that our proposed algorithm can produce sharp high-resolution images with few ringing or jaggy artifacts, and our results have high values of the objective assessment parameters.Keywords
This publication has 14 references indexed in Scilit:
- Image Super-Resolution Using Deep Convolutional NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- Caffe2014
- Removing JPEG blocking artifacts using machine learning2014
- Image Super-Resolution with Fast Approximate Convolutional Sparse Coding2014
- Anchored Neighborhood Regression for Fast Example-Based Super-Resolution2013
- Restoring an Image Taken through a Window Covered with Dirt or Rain2013
- Contour Detection and Hierarchical Image SegmentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2010
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004
- Example-based super-resolutionIEEE Computer Graphics and Applications, 2002
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998