[4eyes] 3D modeling with single-pixel cameras

[Pradeep Sen]

Hmm... very interesting.  It seems that they simply took
our dual photography idea and did shape from shading on
that without citing our original work:

http://dl.acm.org/citation.cfm?id=1073204.1073257

So their statements such as:

     Previous experiments in single-pixel computational
     imaging (9, 14, 16) were restricted to relatively
     small (less than 10 cm) two-dimensional (2D) images,
     mainly of 2D template objects or 2D outlines of 3D objects.

are blatantly false.  We show in Fig. 4 and example
of a scene taken with a single pixel camera (well before that
other single pixel camera work) that is a couple of feet on a side.

They were probably unfamiliar with the dual photography
work, but still I would have expected a more thorough
review process from a journal like Science!

If you told me that I could take the shading curve in
Fig. 13 of our paper and simply apply shape-from-shading
to that and get a paper in Science, I would have thought
you were crazy!

-Pradeep





On 2013-05-24 23:48, Ismo Rakkolainen wrote:
> Hi
>
> 3D object capture with single-pixel cameras?
> No problem. See 
> http://www.sciencemag.org/content/340/6134/844.full.pdf
>
> IsmoR
>
> _______________________________________________
> Ilab-users mailing list
> Ilab-users at lists.cs.ucsb.edu
> https://lists.cs.ucsb.edu/mailman/listinfo/ilab-users

-- 
Pradeep Sen
Associate Professor
UCSB Advanced Graphics Lab
Dept. of Electrical & Computer Engineering
University of California, Santa Barbara
Santa Barbara, CA 93106-9560