Coupled Deep Autoencoder for Single Image Super-Resolution

Sparse coding has been widely applied to learning-based single image super-resolution (SR) and has obtained promising performance by jointly learning effective representations for low-resolution (LR) and high-resolution (HR) image patch pairs. However, the resulting HR images often suffer from ringi...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on cybernetics 2017-01, Vol.47 (1), p.27-37
Main Authors: Zeng, Kun, Yu, Jun, Wang, Ruxin, Li, Cuihua, Tao, Dacheng
Format: Article
Language:English
Subjects:
Autoencoder
Blurring
deep learning
Dictionaries
Encoding
Experimentation
Feature extraction
Image coding
Image reconstruction
Image resolution
Machine learning
Manifolds
Neural networks
Representations
single image super-resolution (SR)
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Sparse coding has been widely applied to learning-based single image super-resolution (SR) and has obtained promising performance by jointly learning effective representations for low-resolution (LR) and high-resolution (HR) image patch pairs. However, the resulting HR images often suffer from ringing, jaggy, and blurring artifacts due to the strong yet ad hoc assumptions that the LR image patch representation is equal to, is linear with, lies on a manifold similar to, or has the same support set as the corresponding HR image patch representation. Motivated by the success of deep learning, we develop a data-driven model coupled deep autoencoder (CDA) for single image SR. CDA is based on a new deep architecture and has high representational capability. CDA simultaneously learns the intrinsic representations of LR and HR image patches and a big-data-driven function that precisely maps these LR representations to their corresponding HR representations. Extensive experimentation demonstrates the superior effectiveness and efficiency of CDA for single image SR compared to other state-of-the-art methods on Set5 and Set14 datasets.
ISSN:2168-2267
2168-2275
DOI:10.1109/TCYB.2015.2501373