SLIDE 1
SVD Applications CS322030 Mar 2009 gaussian 1.0; no noise gaussian - - PowerPoint PPT Presentation
SVD Applications CS322030 Mar 2009 gaussian 1.0; no noise gaussian - - PowerPoint PPT Presentation
SVD Applications CS322030 Mar 2009 gaussian 1.0; no noise gaussian 1.0; noise 0.005 motion blur; no noise motion blur; noise 0.005 1 1 0.9 0.9 0.8 0.8 0.7 0.7 0.6 0.6 0.5 0.5 0.4 0.4 0.3 0.3 0.2 0.2 0.1 0.1 0 0 0 200
SLIDE 2
SLIDE 3
gaussian 1.0; noise 0.005 gaussian 1.0; no noise motion blur; no noise motion blur; noise 0.005
SLIDE 4
motion blur gaussian, stdev = 1.0 singular value vs. index, 32x32 inverse problem
200 400 600 800 1000 1200 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1 200 400 600 800 1000 1200 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1
SLIDE 5
gaussian 1.0; noise 0.005; r = 1024, 900, 400 gaussian 1.0; no noise; r = 1024 motion blur; no noise; r = 1024 motion blur; noise 0.005; r = 1024, 990, 550
SLIDE 6
Figure 1 High quality single image motion-deblurring. The left sub-figure shows one captured image using a hand-held camera under dim light. It is severely blurred by an unknown kernel. The right sub-figure shows our deblurred image result computed by estimating both the blur kernel and the unblurred latent image. We show several close-ups of blurred/unblurred image regions for comparison.
[Shan, Jia, and Agarwala, SIGGRAPH 2008]