| Date |
5-6-2007 |
| Time |
11:00 |
| Room/Location |
DISI- Sala conferenze 322-3° piano |
| Title |
Movie Denoising by Average of Warped Lines |
| Speaker |
Dott. Marcelo Bertalmio |
| Affiliation |
Universitat Pompeu Fabra, Barcelona, Spain |
| Link |
http://www.upf.edu/english/web/
|
| Abstract |
In this talk we will present an efficient method for movie
denoising that does not require any motion estimation. The method is
based on the well known fact that averaging several realizations of a
random variable reduces the variance. For each pixel to be denoised we
look for close similar samples along the level surface passing through
it. With these similar samples we estimate the denoised pixel. The
method to find close similar samples is done via warping lines in
spatio-temporal neighborhoods. For that end we will present an
algorithm based on a method for epipolar line matching in stereo pairs
which has complexity O(N) where N is the number of columns in the
image. In this way the algorithm is computationally efficient.
Furthermore, we will show that the presented method is unsupervised
and can deal with different types of noise while respecting the visual
details on the movie frames.
|