Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/77326
Title: Structure-preserving image super-resolution via contextualized multitask learning
Authors: Shi, Y
Wang, K 
Chen, C
Xu, L
Lin, L
Keywords: Context learning
Convolutional network
Multitask learning
Structure-preserving image super-resolution (SR)
Issue Date: 2017
Publisher: Institute of Electrical and Electronics Engineers
Source: IEEE transactions on multimedia, 2017, v. 19, no. 127938379, p. 2804-2815 How to cite?
Journal: IEEE transactions on multimedia 
Abstract: Single-image super-resolution (SR), which refers to reconstructing a higher resolution image from the observed low-resolution (LR) image, has received substantial attention due to its tremendous application potentials. Despite the breakthroughs of recently proposed SR methods using convolutional neural networks, their generated results usually lack of preserving structural (high-frequency) details. In this paper, regarding global boundary context and residual context as complimentary information for enhancing structural details in image restoration, we develop a contextualized multitask learning framework to address the SR problem. Specifically, our method first extracts convolutional features from the input LR image and applies one deconvolutional module to interpolate the LR feature maps in a content-adaptive way. Then, the resulting feature maps are fed into two branched subnetworks. On several standard benchmarks (e.g., Set5, Set14, and BSD200 ), our extensive evaluations demonstrate the effectiveness of our SR method on achieving both higher restoration quality and computational efficiency compared with several state-of-the-art SR approaches.
URI: http://hdl.handle.net/10397/77326
ISSN: 1520-9210
EISSN: 1941-0077
DOI: 10.1109/TMM.2017.2711263
Appears in Collections:Journal/Magazine Article

Access
View full-text via PolyU eLinks SFX Query
Show full item record

SCOPUSTM   
Citations

14
Last Week
1
Last month
Citations as of May 27, 2020

WEB OF SCIENCETM
Citations

9
Last Week
1
Last month
Citations as of May 26, 2020

Page view(s)

99
Last Week
6
Last month
Citations as of May 6, 2020

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.