Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/67512
Title: Convolutional sparse coding for image super-resolution
Authors: Gu, S
Zuo, W
Xie, Qi
Meng, D
Feng, X
Zhang, L 
Keywords: Image coding
Dictionaries
Convolutional codes
Image resolution
Convolution
Image reconstruction
Encoding
Issue Date: 2015
Publisher: Institute of Electrical and Electronics Engineers
Source: 2015 IEEE International Conference on Computer Vision (ICCV), Santiago, Chile, 7-13 Dec 2015, p.1823-1831 How to cite?
Abstract: Most of the previous sparse coding (SC) based super resolution (SR) methods partition the image into overlapped patches, and process each patch separately. These methods, however, ignore the consistency of pixels in overlapped patches, which is a strong constraint for image reconstruction. In this paper, we propose a convolutional sparse coding (CSC) based SR (CSC-SR) method to address the consistency issue. Our CSC-SR involves three groups of parameters to be learned: (i) a set of filters to decompose the low resolution (LR) image into LR sparse feature maps, (ii) a mapping function to predict the high resolution (HR) feature maps from the LR ones, and (iii) a set of filters to reconstruct the HR images from the predicted HR feature maps via simple convolution operations. By working directly on the whole image, the proposed CSC-SR algorithm does not need to divide the image into overlapped patches, and can exploit the image global correlation to produce more robust reconstruction of image local structures. Experimental results clearly validate the advantages of CSC over patch based SC in SR application. Compared with state-of-the-art SR methods, the proposed CSC-SR method achieves highly competitive PSNR results, while demonstrating better edge and texture preservation performance.
URI: http://hdl.handle.net/10397/67512
ISBN: 978-1-4673-8391-2 (electronic)
978-1-4673-8390-5 (USB)
EISSN: 2380-7504
DOI: 10.1109/ICCV.2015.212
Appears in Collections:Conference Paper

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

SCOPUSTM   
Citations

17
Citations as of Sep 16, 2017

WEB OF SCIENCETM
Citations

12
Citations as of Sep 23, 2017

Page view(s)

6
Last Week
1
Last month
Checked on Sep 24, 2017

Google ScholarTM

Check

Altmetric



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