untitledLei Zhang¡¯s homepage

 

 

Weisheng Dong, Lei Zhang, Guangming Shi, and Xin Li

¡°Nonlocally Centralized Sparse Representation for Image Restoration,¡±

IEEE Trans. on Image Processing, vol. 22, no. 4, pp. 1620-1630, Apr. 2013.

 

Paper: download here

Code: download here

 

Part A: Results on Image Denoising

 

Notes:

(1)   The denoising method in [1] is labeled as ¡°SAPCA-BM3D¡±;

(2)   The denoising method in [2] is labeled as ¡°LSSC¡±;

(3)   The denoising method in [3] is labeled as ¡°EPLL¡±;

(4)   The proposed denoising method is labeled as ¡°NCSR¡±.

For example, the denoised image by the method NCSR on image Girl is labeled as ¡°NCSR_Girl¡±. Other denoised images are labeled similarly.

 

The denoising results on Lena

Download images

The denoising results on Monarch

Download images

The denoising results on Barbara

Download images

The denoising results on Boat                      

Download images

The denoising results on C. Man                    

Download images

The denoising results on Couple                    

Download images

The denoising results on F. Print                    

Download images

The denoising results on Hill                       

Download images

The denoising results on House                     

Download images

The denoising results on Man                       

Download images

The denoising results on Peppers   

Download images

The denoising results on Straw          

Download images

 

 

Part B: Results on Image Deblurring

 

Notes:

(1)   The deblurring method in [4] is labeled as ¡°FISTA¡±;

(2)   The deblurring method in [5] is labeled as ¡°l0-sparse¡±;

(3)   The deblurring method in [6] is labeled as ¡°IDD-BM3D¡±;

(4)   The deblurring method in [7] is labeled as ¡°ASDS-Reg¡±;

(5)   The deblurring method in [8] is labeled as ¡°Fergus¡±;

(6)   The deblurring method in [11] is labeled as ¡°TVMM¡±;

(7)   The proposed denoising method is labeled as ¡°NCSR¡±.

For example, the deblurred image by the method NCSR on image Butterfly is labeled as ¡°NCSR_Butterfly¡±. Other deblurred images are labeled similarly.

 

Experiment 1:  9¡Á9 uniform blur kernel, noise level

                        Some additional deblurring results by the proposed NCSR method with different parameters:  Download images

 

The deblurring results on Butterfly                     

Download images

The deblurring results on Boats                        

Download images

The deblurring results on Cameraman                  

Download images

The deblurring results on House                       

Download images

The deblurring results on Parrot                       

Download images

The deblurring results on Lena                        

Download images

The deblurring results on Barbara                      

Download images

The deblurring results on Starfish                      

Download images

The deblurring results on Peppers                      

Download images

The deblurring results on Leaves                       

Download images

 

Experiment 2: Gaussian blur kernel (standard deviation 1.6), noise level

                        Some additional deblurring results by the proposed NCSR method with different parameters:  Download images

 

The deblurring results on Butterfly                     

Download images

The deblurring results on Boats                        

Download images

The deblurring results on Cameraman                  

Download images

The deblurring results on House                       

Download images

The deblurring results on Parrot                       

Download images

The deblurring results on Lena                        

Download images

The deblurring results on Barbara                      

Download images

The deblurring results on Starfish                      

Download images

The deblurring results on Peppers                      

Download images

The deblurring results on Leaves                       

Download images

 

Experiment 3:  Motion deblurring

The deblurring results on Oldman                      

Download images

The deblurring results on lyndsey2                      

Download images

The deblurring results on Test7                         

Download images

 

Experiment 4:  6 typical deblurring experiments presented in [6]

The deblurring results on Cameraman256                      

Download images

The deblurring results on House                    

Download images

The deblurring results on Lena512                       

Download images

The deblurring results on Barbara

Download images

 

 

Part C: Results on Image Super-resolution

 

Notes:

(1)   The super-resolution method in [9] is labeled as ¡°TV¡±;

(2)   The super-resolution method in [10] is labeled as ¡°Sparse¡±;

(3)   The super-resolution method in [7] is labeled as ¡°ASDS-Reg¡±;

(4)   The proposed super-resolution method is labeled as ¡°NCSR¡±.

For example, the high resolution (HR) image reconstructed by the method NCSR on image Girl is labeled as ¡°NCSR_Girl¡±. Other super-resolution results labeled similarly.

 

Experiment 1: Super-resolution on noiseless images

 

The HR images with scalar factor 3 on Butterfly             

Download images

The HR images with scalar factor 3 on Flower              

Download images

The HR images with scalar factor 3 on Girl                 

Download images

The HR images with scalar factor 3 on Parthenon            

Download images

The HR images with scalar factor 3 on Parrot               

Download images

The HR images with scalar factor 3 on Raccoon             

Download images

The HR images with scalar factor 3 on Bike                

Download images

The HR images with scalar factor 3 on Hat                 

Download images

The HR images with scalar factor 3 on Plants               

Download images

 

Experiment 2: Super-resolution on noisy images

Gaussian white noise with standard deviation 5 is added to the LR images to simulate the noisy low resolution images.

 

The HR images with scalar factor 3 on Butterfly             

Download images

The HR images with scalar factor 3 on Flower              

Download images

The HR images with scalar factor 3 on Girl                 

Download images

The HR images with scalar factor 3 on Parthenon            

Download images

The HR images with scalar factor 3 on Parrot               

Download images

The HR images with scalar factor 3 on Raccoon             

Download images

The HR images with scalar factor 3 on Bike                

Download images

The HR images with scalar factor 3 on Hat                 

Download images

The HR images with scalar factor 3 on Plants               

Download images

 

References

 

[1]     K. Dabov, A. Foi, V. Katkovnik, and K. Egiazarian, ¡°BM3D  image denoising with shape-adaptive principal component analysis,¡± Proc. Workshop on Signal Processing with Adaptive Sparse Structured Representation (SPARS¡¯09), Saint-Malo, Fance, Apr. 2009.

[2]     J. Mairal, F. Bach, J. Ponce, G. Sapiro and A. Zisserman, ¡°Non-Local Sparse Models for Image Restoration,¡± in Proc. IEEE International Conference on Computer Vision, Tokyo, Japan, 2009.

[3]     D. Zoran and Y. Weiss, ¡°From learning models of natural image patches to whole image restoration,¡± in Proc. IEEE Int. Conf. on Computer Vision (ICCV), 2011.

[4]     A. Beck and M. Teboulle, ¡°Fast gradient-based algorithms for constrained total variation image denoising and deblurring problems,¡± IEEE Trans. on Image Process., vol. 18, no. 11, pp. 2419-2434, Nov. 2009.

[5]     J. Portilla, ¡°Image restoration through L0 analysis-based sparse optimization in tight frames,¡± in Proc. IEEE Int. conf. Image Process., pp. 3909-3912, Nov. 2009.

[6]     A. Danielyan, V. Katkovnik, and K. Egiazarian, ¡°BM3D frames and variational image deblurring,¡± IEEE Trans. on Image Processing, vol. 21, no. 4, Apr. 2012.

[7]     W. Dong, L. Zhang, G. Shi, and X. Wu, ¡°Image deblurring and super-resolution by adaptive sparse domain selection and adaptive regularization,¡± IEEE Trans. on Image Processing, vol. 20, no. 7, pp. 1838-1857, July 2011.

[8]     R. Fergus, B. Singh, A. Hertzmann, S. T. Roweis, and W. T. Freeman, ¡°Removing camera shake from a single image,¡± ACM Trans. Graph. (SIGGRAPH), pages 787-794, 2006.

[9]     A. Marquina, and S. J. Osher, ¡°Image super-resolution by TV-regularization and Bregman iteration,¡± J. Sci. Comput., vol. 37, pp. 367-382, 2008.

[10] J. Yang, J. Wright, Y. Ma, and T. Huang, ¡°Image super-resolution as sparse representation of raw image patches,¡± IEEE Computer Vision and Pattern Recognition, vol. 1, pp. 1-8, Jun. 2008.

[11] J. Oliveira, J. M. Bioucas-Dias, and M. Figueiredo, ¡°Adaptive total variation image deblurring: a majorization-minimization approach,¡± Signal Processing, vol. 89, no. 9, pp. 1683-1693, Sep. 2009.