Welcome
Weizmann Institute of Science
Department of Mathematics and Computer Science
Introduction to Computer Vision
Fall Semester, 2019
News
Most recent posts:
Hi,
Please note that Q2, question #2 in example exam from 2011 (the first exam in the zip file)...
(by benfei 15 Feb 2019 21:40, posts: 1)
(by benfei 15 Feb 2019 21:40, posts: 1)
Hi,
It seems that DIP may suffer from what’s called “dataset optimization”, which can explain the...
(by benfei 03 Feb 2019 12:50, posts: 1)
(by benfei 03 Feb 2019 12:50, posts: 1)
Many of you told us that couldn’t get near the +29dB boost (PSNR) reported in the DIP paper. We a...
(by benfei 31 Jan 2019 19:50, posts: 1)
(by benfei 31 Jan 2019 19:50, posts: 1)
As in align_image(), out-of-bounds pixels (w.r.t frame's bounds) should be NaN.
(by benfei 17 Jan 2019 12:30, posts: 2)
(by benfei 17 Jan 2019 12:30, posts: 2)
Q: what should error_map return?
A: A tuple of (diff, diff_bounds).
Q: how should we use bounds...
(by benfei 17 Jan 2019 10:14, posts: 1)
(by benfei 17 Jan 2019 10:14, posts: 1)
you should align all the frames to frame number ref_idx, take the median, and plug it back in...
(by benfei 17 Jan 2019 10:00, posts: 2)
(by benfei 17 Jan 2019 10:00, posts: 2)
the value MAX_I in wikipedia is actually maxval - minval.
if zero_nans=True, you should indeed...
(by benfei 17 Jan 2019 09:56, posts: 2)
(by benfei 17 Jan 2019 09:56, posts: 2)
bounds in the argument is the valid bounds of the given images (image and reference).
bounds in...
(by benfei 17 Jan 2019 09:53, posts: 2)
(by benfei 17 Jan 2019 09:53, posts: 2)
In example attached in the notebook, name is used in the title of the "shift vs....
(by benfei 17 Jan 2019 09:50, posts: 2)
(by benfei 17 Jan 2019 09:50, posts: 2)
hi,
the aligned video should include nan pixels or we should fill them?
thanks
(by Roee Zamir 16 Jan 2019 21:21, posts: 2)
(by Roee Zamir 16 Jan 2019 21:21, posts: 2)