Image Super-Resolution Using Deep Convolutional Networks
This work addresses image enhancement for applications like photography or video, but it is incremental as it builds on existing deep learning and sparse-coding methods.
The authors tackled single image super-resolution by proposing a deep convolutional neural network that learns an end-to-end mapping from low- to high-resolution images, achieving state-of-the-art restoration quality and fast speed for practical use.
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.