Learning a deep convolutional network for image super-resolution
Refereed conference paper presented and published in conference proceedings


Times Cited
Altmetrics Information
.

Other information
AbstractWe 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) [15] 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. © 2014 Springer International Publishing.
All Author(s) ListDong C., Loy C.C., He K., Tang X.
Name of Conference13th European Conference on Computer Vision, ECCV 2014
Start Date of Conference06/09/2014
End Date of Conference12/09/2014
Place of ConferenceZurich
Country/Region of ConferenceSwitzerland
Detailed descriptionETH Zurich
Year2014
Month1
Day1
Volume Number8692 LNCS
Issue NumberPART 4
PublisherSpringer Verlag
Place of PublicationGermany
Pages184 - 199
ISBN9783319105925
ISSN1611-3349
LanguagesEnglish-United Kingdom
Keywordsdeep convolutional neural networks, Super-resolution

Last updated on 2020-18-09 at 01:39