Image Super-Resolution Using Deep Convolutional Networks
Publication in refereed journal

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) 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.
All Author(s) ListDong C., Loy C.C., He K., Tang X.
Journal nameIEEE Transactions on Pattern Analysis and Machine Intelligence
Volume Number38
Issue Number2
PublisherInstitute of Electrical and Electronics Engineers
Place of PublicationUnited States
Pages295 - 307
LanguagesEnglish-United Kingdom
Keywordsdeep convolutional neural networks, sparse coding, Super-resolution

Last updated on 2021-10-09 at 23:56