CVNEDec 31, 2014

Image Super-Resolution Using Deep Convolutional Networks

arXiv:1501.00092v39285 citations
Originality Incremental advance
AI Analysis

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.

Code Implementations60 repos

Data from Papers with Code (CC-BY-SA-4.0)

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes