SINGLE IMAGE SUPER-RESOLUTION USING SPARSE REPRESENTATIONS WITH STRUCTURE CONSTRAINTS

被引:0
作者
Ferreira, J. C. [1 ,3 ]
Le Meur, O. [1 ]
Guillemot, C. [1 ]
da Silva, E. A. B. [2 ]
Carrijo, G. A. [3 ]
机构
[1] INRIA, SIROCCO Res Team, Paris, France
[2] Univ Fed Rio de Janeiro, COPPE, Rio de Janeiro, Brazil
[3] UFU, FEELT, Rio De Janeiro, Brazil
来源
2014 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) | 2014年
关键词
super-resolution; sparse representations; structure tensors;
D O I
暂无
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
This paper describes a new single-image super-resolution algorithm based on sparse representations with image structure constraints. A structure tensor based regularization is introduced in the sparse approximation in order to improve the sharpness of edges. The new formulation allows reducing the ringing artefacts which can be observed around edges reconstructed by existing methods. The proposed method, named Sharper Edges based Adaptive Sparse Domain Selection (SE-ASDS), achieves much better results than many state-of-the-art algorithms, showing significant improvements in terms of PSNR (average of 29.63, previously 29.19), SSIM (average of 0.8559, previously 0.8471) and visual quality perception.
引用
收藏
页码:3862 / 3866
页数:5
相关论文
共 18 条
[1]   Super-resolution through neighbor embedding [J].
Chang, H ;
Yeung, DY ;
Xiong, Y .
PROCEEDINGS OF THE 2004 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOL 1, 2004, :275-282
[2]  
Dai S., 2007, Computer Vision and Pattern Recognition, P1, DOI DOI 10.1109/CVPR.2007.383028
[3]   SoftCuts: A Soft Edge Smoothness Prior for Color Image Super-Resolution [J].
Dai, Shengyang ;
Han, Mei ;
Xu, Wei ;
Wu, Ying ;
Gong, Yihong ;
Katsaggelos, Aggelos K. .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2009, 18 (05) :969-981
[4]   An iterative thresholding algorithm for linear inverse problems with a sparsity constraint [J].
Daubechies, I ;
Defrise, M ;
De Mol, C .
COMMUNICATIONS ON PURE AND APPLIED MATHEMATICS, 2004, 57 (11) :1413-1457
[5]   A NOTE ON THE GRADIENT OF A MULTIIMAGE [J].
DIZENZO, S .
COMPUTER VISION GRAPHICS AND IMAGE PROCESSING, 1986, 33 (01) :116-125
[6]   Image Deblurring and Super-Resolution by Adaptive Sparse Domain Selection and Adaptive Regularization [J].
Dong, Weisheng ;
Zhang, Lei ;
Shi, Guangming ;
Wu, Xiaolin .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2011, 20 (07) :1838-1857
[7]   Non-local adaptive structure tensors Application to anisotropic diffusion and shock filtering [J].
Dore, Vincent ;
Moghaddam, Reza Farrahi ;
Cheriet, Mohamed .
IMAGE AND VISION COMPUTING, 2011, 29 (11) :730-743
[8]   Multiscale shape and detail enhancement from multi-light image collections [J].
Fattal, Raanan ;
Agrawala, Maneesh ;
Rusinkiewicz, Szymon .
ACM TRANSACTIONS ON GRAPHICS, 2007, 26 (03)
[9]   Example-based super-resolution [J].
Freeman, WT ;
Jones, TR ;
Pasztor, EC .
IEEE COMPUTER GRAPHICS AND APPLICATIONS, 2002, 22 (02) :56-65
[10]  
Irani M., 1993, Journal of Visual Communication and Image Representation, V4, P324, DOI 10.1006/jvci.1993.1030