Question Only: provenance of code ?

[mxbdev]

HI, I'm curious whether you were able to get the original code from the Google authors as a starting point, or did you develop everything from scratch? Do you know if the Google authors released any code and if so, where to find it?

I will compare your analysis with their paper and see if I can shed further light on what you've discovered.

Thanks, Max Buchheit

[kunzmi]

Hi,

no, this is all developed from scratch based on the paper and my knowledge in image processing. As far as I know there is no other implementation of the algorithm available in source code, neither from Google nor any other. If you find any, I'd be happy to hear about it, to see how it solves some of the open questions in the paper. Also Google is not very communicative, I tried to contact the authors to get some answers because the paper alone is just not enough to get a reproducible implementation, but I never got an answer. So I had to sit down and think about it myself ;)

Michael

[hasanlatif]

please find the another implementation of same paper https://github.com/JVision/Handheld-Multi-Frame-Super-Resolution

[hasanlatif]

Hi please find another implementation at https://github.com/JVision/Handheld-Multi-Frame-Super-Resolution regards,

[kunzmi]

Thanks @hasanlatif, I know the linked project and I should have been more clear with "I know no other implementation": I meant "operational implementation", code that one can run and get an image as result... The linked project consists only of a few lines of code and tries to implement only a tiny part of the paper. It is far from showing that the algorithm presented in the paper actually works or not ;)

Cheers, Michael