Anisotropic Total Variation Method for Text Image Super-Resolution

2008 ◽  
Author(s):  
Battulga Bayarsaikhan ◽  
Younghee Kwon ◽  
Jin Hyung Kim
Keyword(s):  
Total Variation ◽  
Super Resolution ◽  
Variation Method ◽  
Image Super Resolution ◽  
Anisotropic Total Variation

scholarly journals Low-Rank Total Variation for Image Super-Resolution

2013 ◽  
pp. 155-162 ◽  
Author(s):  
Feng Shi ◽  
Jian Cheng ◽  
Li Wang ◽  
Pew-Thian Yap ◽  
Dinggang Shen
Keyword(s):  
Total Variation ◽  
Super Resolution ◽  
Low Rank ◽  
Image Super Resolution

scholarly journals LRTV: MR Image Super-Resolution With Low-Rank and Total Variation Regularizations

2015 ◽  
Vol 34 (12) ◽  
pp. 2459-2466 ◽  
Author(s):  
Feng Shi ◽  
Jian Cheng ◽  
Li Wang ◽  
Pew-Thian Yap ◽  
Dinggang Shen
Keyword(s):  
Total Variation ◽  
Super Resolution ◽  
Low Rank ◽  
Mr Image ◽  
Image Super Resolution

scholarly journals Spatially Adaptive Tensor Total Variation-Tikhonov Model for Depth Image Super Resolution

IEEE Access ◽  
2017 ◽  
Vol 5 ◽  
pp. 13857-13867 ◽  
Author(s):  
Gang Zhong ◽  
Sen Xiang ◽  
Peng Zhou ◽  
Li Yu
Keyword(s):  
Total Variation ◽  
Super Resolution ◽  
Depth Image ◽  
Spatially Adaptive ◽  
Image Super Resolution

scholarly journals TV2++: A Novel Spatial-Temporal Total Variation for Super Resolution with Exponential-type Norm

2020 ◽  
Author(s):  
Lizhen Deng ◽  
Zhetao Zhou ◽  
Guoxia Xu ◽  
Hu Zhu ◽  
Bing-Kun Bao
Keyword(s):  
Total Variation ◽  
Exponential Type ◽  
Optimization Problems ◽  
Super Resolution ◽  
Low Rank ◽  
Good Effect ◽  
Total Variation Regularization ◽  
Time Dimension ◽  
Tv Regularization ◽  
Image Super Resolution

Abstract Recently, many super-resolution algorithms have been proposed to recover high resolution images to improve visualization and help better analyze images. Among them, total variation regularization (TV) methods have been proven to have a good effect in retaining image edge information. However, these TV methods do not consider the temporal correlation between images. Our algorithm designs a new TV regularization (TV2++) to take advantage of the time dimension information of the images, further improving the utilization of useful information in the images. In addition, the union of global low rank regularization and TV regularization further enhances the image super resolution recovery. And we extend the exponential-type penalty (ETP) function on singular values of a matrix to enhance low-rank matrix recovery. A novel image super-resolution algorithm based on the ETP norm and TV2++ regularization is proposed. And the alternating direction method of multipliers (ADMM) is applied to solve the optimization problems effectively. Numerous experimental results prove that the proposed algorithm is superior to other algorithms.

scholarly journals TV2++: A Novel Spatial-Temporal Total Variation for Super Resolution with Exponential-type Norm

2020 ◽  
Author(s):  
Lizhen Deng ◽  
Zhetao Zhou ◽  
Guoxia Xu ◽  
Hu Zhu ◽  
Bing-Kun Bao
Keyword(s):  
Total Variation ◽  
Exponential Type ◽  
Optimization Problems ◽  
Super Resolution ◽  
Low Rank ◽  
Good Effect ◽  
Total Variation Regularization ◽  
Time Dimension ◽  
Tv Regularization ◽  
Image Super Resolution

Abstract Recently, many super-resolution algorithms have been proposed to recover high resolution images to improve visualization and help better analyze images. Among them, total variation regularization (TV) methods have been proven to have a good effect in retaining image edge information. However, these TV methods do not consider the temporal correlation between images. Our algorithm designs a new TV regularization (TV2++) to take advantage of the time dimension information of the images, further improving the utilization of useful information in the images. In addition, the union of global low rank regularization and TV regularization further enhances the image super resolution recovery. And we extend the exponential-type penalty (ETP) function on singular values of a matrix to enhance low-rank matrix recovery. A novel image super-resolution algorithm based on the ETP norm and TV2++ regularization is proposed. And the alternating direction method of multipliers (ADMM) is applied to solve the optimization problems effectively. Numerous experimental results prove that the proposed algorithm is superior to other algorithms.

Sign in / Sign up

Export Citation Format

Share Document