Robust Single Image Super-Resolution via Deep Networks With Sparse Prior

Single image super-resolution (SR) is an ill-posed problem, which tries to recover a high-resolution image from its low-resolution observation. To regularize the solution of the problem, previous methods have focused on designing good priors for natural images, such as sparse representation, or dire...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on image processing Jg. 25; H. 7; S. 3194 - 3207
Hauptverfasser: Ding Liu, Zhaowen Wang, Bihan Wen, Jianchao Yang, Wei Han, Huang, Thomas S.
Format: Journal Article
Sprache:Englisch
Veröffentlicht: United States IEEE 01.07.2016
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
Coding
deep neural networks
Degradation
Dictionaries
Image coding
Image resolution
image super-resolution
Learning
Machine learning
Networks
Neural networks
Scaling factors
sparse coding
Training
sparse coding
deep neural networks
Image super-resolution
ISSN:1057-7149, 1941-0042
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Single image super-resolution (SR) is an ill-posed problem, which tries to recover a high-resolution image from its low-resolution observation. To regularize the solution of the problem, previous methods have focused on designing good priors for natural images, such as sparse representation, or directly learning the priors from a large data set with models, such as deep neural networks. In this paper, we argue that domain expertise from the conventional sparse coding model can be combined with the key ingredients of deep learning to achieve further improved results. We demonstrate that a sparse coding model particularly designed for SR can be incarnated as a neural network with the merit of end-to-end optimization over training data. The network has a cascaded structure, which boosts the SR performance for both fixed and incremental scaling factors. The proposed training and testing schemes can be extended for robust handling of images with additional degradation, such as noise and blurring. A subjective assessment is conducted and analyzed in order to thoroughly evaluate various SR techniques. Our proposed model is tested on a wide range of images, and it significantly outperforms the existing state-of-the-art methods for various scaling factors both quantitatively and perceptually.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:1057-7149
1941-0042
DOI:10.1109/TIP.2016.2564643