Image Super-Resolution Using Deep Convolutional Networks
Chao Dong, Chen Change Loy, Kaiming He et al. · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2015
We propose a deep learning method for single image super-resolution (SR). Our method directly learns an end-to-end mapping between the low/high-resolution images. The mapping is represented as a deep convolutional neural network (CNN) that takes the low-resolution image as the input and outputs the high-resolution one. We further show that traditional sparse-coding-based SR methods can also be viewed as a deep convolutional network. But unlike traditional methods that handle each component separately, our method jointly optimizes all layers. Our deep CNN has a lightweight structure, yet demonstrates state-of-the-art restoration quality, and achieves fast speed for practical on-line usage. We explore different network structures and parameter settings to achieve trade-offs between performance and speed. Moreover, we extend our network to cope with three color channels simultaneously, and show better overall reconstruction quality.
Cited by 10,027 works. doi:10.1109/tpami.2015.2439281 Open-access PDF
Authors
References
- ImageNet classification with deep convolutional neural networks
- Gradient-based learning applied to document recognition
- ImageNet: A large-scale hierarchical image database
- Backpropagation Applied to Handwritten Zip Code Recognition
- Caffe
- Image quality assessment: from error visibility to structural similarity
- Rectified Linear Units Improve Restricted Boltzmann Machines
- Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
- A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics
- ImageNet: A large-scale hierarchical image database