Image Super-Resolution Using Deep Convolutional Networks

TL;DR

This paper introduces a deep convolutional neural network for single image super-resolution that learns an end-to-end mapping, achieving state-of-the-art quality with fast processing and multi-channel extension.

Contribution

It presents a novel deep CNN architecture for super-resolution that jointly optimizes all layers, outperforming traditional sparse-coding methods in quality and speed.

Findings

Achieves state-of-the-art super-resolution quality.

Demonstrates fast processing suitable for online use.

Effectively handles three color channels simultaneously.

Abstract

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.