Tom Sharpless wrote:
Hi
If OpenSurf is legitimately GPL there cannot be a patent problem with
SURF. So why not use it?
From what I have seem, it pretty much uses the algorithm as it is
described in the SURF patent, so I doubt that it is a safe alternative
in that sense.
> It is the fastest interest point algorithm
I know of, and almost if not just as good as SIFT. Both do their job
excellently and I can't see much likelihood of Pablo -- or anyone else
-- inventing something different that works equally well. Anything is
possible, of course, but....
The primary goal is not to create a superior algorithm to SIFT or SURF,
but to have something that allows us to stitch panoramas without having
worrying too much about patents.
The matching software that we currently have, with the extensions done
by Bruno and Thomas lately should pretty much allow matching of most
types of panoramas for the most common usecases. Of course there will
aways be panoramas which can't be matched automatically.
The problem with using prior information is that it needs to be
specified to the computer program. Some expert users might want to do
this, but the 95% of our users probably won't want to do any of that,
they just want to press one button and have a nice panorama (and most of
them don't actually care if it has one or two smaller errors left,
people also by cheap and crappy cameras...).
A better integration of the RANSAC step with the alignment model we use
might be a good improvement, too.
Btw. what happened to the matching software you were developing?
ciao
Pablo
--
You received this message because you are subscribed to the Google Groups "hugin and
other free panoramic software" group.
A list of frequently asked questions is available at:
http://wiki.panotools.org/Hugin_FAQ
To post to this group, send email to [email protected]
To unsubscribe from this group, send email to
[email protected]
For more options, visit this group at http://groups.google.com/group/hugin-ptx
