Old and New algorithm for Blind Deconvolution thumbnail
Pause
Mute
Subtitles
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

Old and New algorithm for Blind Deconvolution

Published on Jan 23, 201212203 Views

I will discuss blind deconvolution algorithms that have been successfully used in the field of communications for several decades and how they can be adapted to the problem of blind deconvolution of i

Related categories

Chapter list

Old and New Algorithms for Blind Deconvolution00:00
Blind Deblurring01:02
Much Recent Progress01:22
MAP using sparse derivative prior02:16
This talk04:38
Blind Deconvolution in Communication05:39
Blur makes signals Gaussians (Central Limit Theorem) - 108:08
Blur makes signals Gaussians (Central Limit Theorem) - 210:12
Simple Blind Deconvolution Algorithm (Shalvi and Weinstein 1980)10:46
Simple Proof13:01
Proof by pictures15:19
Blind Deconvolution by Maximizing non Gaussianity16:38
Blur makes derivatives more Gaussian18:53
New class of image blind deblurring alglrithms19:52
Measuring non Gaussianity using normalized moments20:41
A new(?) algorithm - 122:21
MAPx;k algorithm23:08
Normalized Sparsity (Krishnan et al. 11)25:41
MAPxk with bilateral filtering (Cho and Lee 09, Hirsch et al. 11)26:33
A new(?) algorithm - 228:24
So what does this buy us?28:27
Conclusions29:32