Rank: 1141 based on 133 downloads (last 30 days) and 1 file submitted
photo

Victor May

E-mail
Company/University
Tel-Aviv University

Personal Profile:
Professional Interests:

 

Watch this Author's files

 

Files Posted by Victor
Updated   File Tags Downloads
(last 30 days)
Comments Rating
26 Nov 2011 Screenshot Image Super-Resolution - Iterative Back Projection Algorithm A simple maximum-likelihood algorithm for super-resolution. Author: Victor May image processing 133 14
  • 4.5
4.5 | 2 ratings
Comments and Ratings by Victor View all
Updated File Comments Rating
05 Jan 2012 Image Super-Resolution - Iterative Back Projection Algorithm A simple maximum-likelihood algorithm for super-resolution. Author: Victor May

Increasing the number of images causes the solution to suffer from overfit. Adding a prior on the image should help. Search the web for papers on priors for super-resolution.

26 Nov 2011 Image Super-Resolution - Iterative Back Projection Algorithm A simple maximum-likelihood algorithm for super-resolution. Author: Victor May

I posted it. It might take a few days until it will show up here.

26 Nov 2011 Image Super-Resolution - Iterative Back Projection Algorithm A simple maximum-likelihood algorithm for super-resolution. Author: Victor May

Hi Imi,
the function SynthDataset has an output called croppedOriginal which crops the original image to the size of the super-resolved image. In order to prevent confusion about this, I've updated the example script to include a mean-square error calculation.

Comments and Ratings on Victor's Files View all
Updated File Comment by Comments Rating
17 Sep 2013 Image Super-Resolution - Iterative Back Projection Algorithm A simple maximum-likelihood algorithm for super-resolution. Author: Victor May yadhul

how can i use this one for video frame.... i want to change low resolution video frame to high resolution video frame how can i do it.. can i do it with this code...

12 Sep 2012 Image Super-Resolution - Iterative Back Projection Algorithm A simple maximum-likelihood algorithm for super-resolution. Author: Victor May Petersen, Steffen B.

When generating the stack of LowRes Images the code only produces a diagonal shift, since the offsets along x and y are identical.

change the following line in SynthDataset:

offsets(i,:)=2*rand -1 --> offset(i,:)=2*rand(2,1)-1

11 May 2012 Image Super-Resolution - Iterative Back Projection Algorithm A simple maximum-likelihood algorithm for super-resolution. Author: Victor May kh, imi

Can some one tell me why we model noise as additive Gaussian noise in most of the super-resolution algorithms.

27 Feb 2012 Image Super-Resolution - Iterative Back Projection Algorithm A simple maximum-likelihood algorithm for super-resolution. Author: Victor May Pfeffer, Yitzi

In order to avoid divergence when using a large number of LR images. Try to use a coefficient smaller than 1 (I tried 0.25) in the update equation for x:
x = x + 0.25*res; instead of x = x + res; This ensures smaller (and safer) steps in the Gradient Descent procedure.

05 Jan 2012 Image Super-Resolution - Iterative Back Projection Algorithm A simple maximum-likelihood algorithm for super-resolution. Author: Victor May kh, imi

well i do add laplasian term as a prior, but i think the problem lies some where else because if you increase number of low resolution images the output destroyed.

Contact us