Blur-Kernel Estimation from Spectral Irregularities

ECCV 2012

Amit Goldstein and Raanan Fattal

Results Page


Page contains additional tests over real and synthetic images.
Instructions: left-click on each image to view in full resolution.
Extracted blur kernels are shown on top of each image.


 


 

Real Images (aquired with motion blur)

Venice

Blurred
Cho,Lee 09'
Our

 


 

Torres Del Paine

Blurred
Cho,Lee 09'
Cho et al. 11'
Our

 


 

Torres Del Paine

Blurred
Cho,Lee 09'
Our

 


 

Real world images taken from Cho et al. 11'

Blurred
Cho,Lee 09'
Krishnan et al. 11'
Levin 11'
Our

 


 

Blurred
Cho,Lee 09'
Cho et al. 11'
Our

 


 

Blurred
Cho,Lee 09'
Cho et al. 11'
Our

 


 

Blurred
Cho,Lee 09'
Cho et al. 11'
Our

 


 

Blurred
Cho,Lee 09'
Cho et al. 11'
Our

 


 

Blurred
Cho,Lee 09'
Cho et al. 11'
Our

 


 

Blurred
Cho,Lee 09'
Cho et al. 11'
Our

 


 

Blurred
Cho,Lee 09'
Cho et al. 11'
Our

 


 

Blurred
Cho,Lee 09'
Cho et al. 11'
Our

 


 

Blurred
Cho,Lee 09'
Cho et al. 11'
Our

 


 

Synthetic Examples

Images below are some of the synthetic images used in our dataset for the quantitative evaluation

Blurred
True Kernel
Cho,Lee 09'
Krishnan et al. 11'
Levin 11'
Our

 


 

Blurred
True Kernel
Cho,Lee 09'
Krishnan et al. 11'
Levin 11'
Our

 


 

Blurred
True Kernel
Cho,Lee 09'
Krishnan et al. 11'
Levin 11'
Our

 


 

Blurred
True Kernel
Cho,Lee 09'
Krishnan et al. 11'
Levin 11'
Our

 


 

Blurred
True Kernel
Cho,Lee 09'
Krishnan et al. 11'
Levin 11'
Our

 


 

Blurred
True Kernel
Cho,Lee 09'
Krishnan et al. 11'
Levin 11'
Our

 


 

Blurred
True Kernel
Cho,Lee 09'
Krishnan et al. 11'
Levin 11'
Our

 


 

Blurred
True Kernel
Cho,Lee 09'
Krishnan et al. 11'
Levin 11'
Our

 


 

Failure cases

Blurred
Cho,Lee 09'
Cho et al. 11'
Our

To further investigate this failure case we obtained another image of the same bridge ("Zakim" in Boston) and computed its autocorrelation function.
The repeating structure in the image (the bridge wires) translated into severe biases to this statistic (and ones at the scale of the blur; larger-scale effects would have not been a major problem).
These biases undermine the ability to whiten the image spectrum and estimate the kernel's power spectrum function.

Similar sharp image
Auto Correlation of sharp image

 


 

Significant spatial variability of the blur is not compatible with our model assumptions

Blurred Image
True PSF
Our Result

 


 

Significant variability in focal blur is not compatible with our model assumptions

Original Image
With synthetic uniform blur
Our Result