SNR, why have you forsaken me ?

I’m not as much on FREAKs reconstruction and blogging as I wished, because I have one really important target for the next 6 months: submitting my thesis before the end of the year.

The dreaded SNR measure

We’ve come up with a nice equation in the past few months (hence, this work is completely unpublished) and after managing to implement it I’m now testing it to show that it is actually outstanding. Or at least that it works. Well, I’d be happy if it just worked ;-)

I’m quite pleased by the current visual state of our work. Even texture deconvolution seems OK, sharpness recovered with few artifacts.

But then, when I want to comfort my opinion by SNR measures, I am always disappointed to get a lower score than the input degraded image.

Deblurring animation, juil. 2012

As they say in the movies, {{something’s going on here}}, and I’d better to find out what. Quickly.