Good Regions to Deblur thumbnail
slide-image
Pause
Mute
Subtitles not available
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

Good Regions to Deblur

Published on Nov 12, 20124146 Views

The goal of single image deblurring is to recover both a latent clear image and an underlying blur kernel from one input blurred image. Recent works focus on exploiting natural image priors or additio

Related categories

Chapter list

Good Regions to Deblur00:00
Image Blur00:03
Uniform Image Blur Model (1)00:24
Uniform Image Blur Model (2)00:46
Related Work01:18
Motivation (1)01:30
Motivation (2)01:56
Motivation (3)02:40
Motivation (4)02:48
Motivation (5)03:07
Motivation (6)03:19
Learning Model (1)03:46
Learning Model (2)04:29
Learning Framework (1)04:57
Learning Framework (2)05:16
Feature Vector05:38
Kernel Similarity Metric06:00
Parameter Learning06:38
Training Data06:51
Inference07:15
Experiments07:35
Experimental Results (1)08:02
Experimental Results (2)08:40
Experimental Results (3)08:59
Experimental Results (4)09:16
Experimental Results (5)09:28
Experimental Results (6)09:38
Results Using Top Ten Subwindows (1)09:52
Results Using Top Ten Subwindows (2)10:10
Quantitative Comparison10:34
Concluding Remarks11:07