en-de
en-sl
en
en-zh
en-fr
en-es
0.25
0.5
0.75
1.25
1.5
1.75
2
From Image Restoration to Compressive Sampling in Computational Photography. A Bayesian Perspective.
Published on 2012-01-235324 Views
the quality of the imaging system or reproducing the scene conditions in order to acquire another image is not an option, computational approaches provide a powerful means for the recovery of lost inf
Related categories
Presentation
From Image Restoration to Compressive Sampling in Computational Photography. A Bayesian Perspective00:00
Outline00:22
Let’s go back some 25 years00:58
Observation Process p(y|x)01:44
Inference03:40
Observation / Restoration04:52
Image Restoration - 105:57
Image Restoration - 209:23
Image Restoration - 311:04
Image Restoration - 412:02
Image Restoration - 513:16
Image Restoration - 616:10
Image Restoration - 716:33
Blind Deconvolution18:03
Taking pairs of images - 120:26
Taking pairs of images - 221:23
Taking pairs of images - 322:15
Taking pairs of images - 422:31
Taking pairs of images - 524:37
Modifying the aperture - 124:43
Modifying the aperture - 225:11
Capturing the Light Field using CS - 125:22
Capturing the Light Field using CS - 225:42
Capturing the Light Field using CS - 325:46
Capturing the Light Field using CS - 425:57
Capturing the Light Field using CS - 526:21
Capturing the Light Field using CS - 626:37
Capturing the Light Field using CS - 726:44
Our prototype - 127:15
Our prototype - 227:48
Our prototype - 327:51
Our prototype - 428:01
Our prototype - 528:03
Our prototype - 628:16
Our prototype - 728:32
Our prototype - 828:35
Our prototype - 928:48
Our prototype - 1028:57
Our prototype - 1129:17
Our prototype - 1229:22
Our prototype - 1329:38
Our prototype - 1429:45
Our prototype - 1529:49
Our prototype - 1629:57
Our prototype - 1730:02
Collaborators - 130:05
Collaborators - 230:26