A Unified Learning Framework for Single Image Super-Resolution

It has been widely acknowledged that learning- and reconstruction-based super-resolution (SR) methods are effective to generate a high-resolution (HR) image from a single low-resolution (LR) input. However, learning-based methods are prone to introduce unexpected details into resultant HR images. Al...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transaction on neural networks and learning systems 2014-04, Vol.25 (4), p.780-792
Main Authors: Yu, Jifei, Gao, Xinbo, Tao, Dacheng, Li, Xuelong, Zhang, Kaibing
Format: Article
Language:English
Subjects:
Algorithms
Applied sciences
Artificial Intelligence
Computer science
control theory
systems
Dictionaries
Estimation
Exact sciences and technology
Example learning-based
Image edge detection
Image enhancement
Image Enhancement - methods
Image Interpretation, Computer-Assisted - methods
Image reconstruction
Image resolution
image super-resolution (SR)
Learning
Learning systems
Matching pursuit algorithms
Neural networks
Pattern Recognition, Automated - methods
Pattern recognition. Digital image processing. Computational geometry
Photography - methods
Production methods
reconstruction-based
Reproducibility of Results
self-similarity
Sensitivity and Specificity
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:It has been widely acknowledged that learning- and reconstruction-based super-resolution (SR) methods are effective to generate a high-resolution (HR) image from a single low-resolution (LR) input. However, learning-based methods are prone to introduce unexpected details into resultant HR images. Although reconstruction-based methods do not generate obvious artifacts, they tend to blur fine details and end up with unnatural results. In this paper, we propose a new SR framework that seamlessly integrates learning- and reconstruction-based methods for single image SR to: 1) avoid unexpected artifacts introduced by learning-based SR and 2) restore the missing high-frequency details smoothed by reconstruction-based SR. This integrated framework learns a single dictionary from the LR input instead of from external images to hallucinate details, embeds nonlocal means filter in the reconstruction-based SR to enhance edges and suppress artifacts, and gradually magnifies the LR input to the desired high-quality SR result. We demonstrate both visually and quantitatively that the proposed framework produces better results than previous methods from the literature.
ISSN:2162-237X
2162-2388
DOI:10.1109/TNNLS.2013.2281313