inferring the kernel: multiscale method input image loop over scales variational bayes upsample...
TRANSCRIPT
![Page 1: Inferring the kernel: multiscale method Input image Loop over scales Variational Bayes Upsample estimates Use multi-scale approach to avoid local minima:](https://reader035.vdocuments.mx/reader035/viewer/2022070305/551477ea550346b0158b5394/html5/thumbnails/1.jpg)
Inferring the kernel: multiscale method
Input image
Loop over scales
Variational
Bayes
Upsample
estimates
Use multi-scale approach to avoid local minima:
Initialize 3x3 blur kernel
Convert tograyscale
Remove gammacorrection
User selects patch from image
![Page 2: Inferring the kernel: multiscale method Input image Loop over scales Variational Bayes Upsample estimates Use multi-scale approach to avoid local minima:](https://reader035.vdocuments.mx/reader035/viewer/2022070305/551477ea550346b0158b5394/html5/thumbnails/2.jpg)
Image ReconstructionInput image
Full resolutionblur estimate
Non-blind deconvolution
(Richardson-Lucy)
Deblurred image
Loop over scales
Variational
Bayes
Upsample
estimates
Initialize 3x3 blur kernel
Convert tograyscale
Remove gammacorrection
User selects patch from image
![Page 3: Inferring the kernel: multiscale method Input image Loop over scales Variational Bayes Upsample estimates Use multi-scale approach to avoid local minima:](https://reader035.vdocuments.mx/reader035/viewer/2022070305/551477ea550346b0158b5394/html5/thumbnails/3.jpg)
![Page 4: Inferring the kernel: multiscale method Input image Loop over scales Variational Bayes Upsample estimates Use multi-scale approach to avoid local minima:](https://reader035.vdocuments.mx/reader035/viewer/2022070305/551477ea550346b0158b5394/html5/thumbnails/4.jpg)
Results on real images
Submitted by people from their own photo collections
Type of camera unknown
Output does contain artifacts– Increased noise
– Ringing
Compares well to existing methods
![Page 5: Inferring the kernel: multiscale method Input image Loop over scales Variational Bayes Upsample estimates Use multi-scale approach to avoid local minima:](https://reader035.vdocuments.mx/reader035/viewer/2022070305/551477ea550346b0158b5394/html5/thumbnails/5.jpg)
Original photograph
![Page 6: Inferring the kernel: multiscale method Input image Loop over scales Variational Bayes Upsample estimates Use multi-scale approach to avoid local minima:](https://reader035.vdocuments.mx/reader035/viewer/2022070305/551477ea550346b0158b5394/html5/thumbnails/6.jpg)
Blur kernel Our output
![Page 7: Inferring the kernel: multiscale method Input image Loop over scales Variational Bayes Upsample estimates Use multi-scale approach to avoid local minima:](https://reader035.vdocuments.mx/reader035/viewer/2022070305/551477ea550346b0158b5394/html5/thumbnails/7.jpg)
Original photographMatlab’s deconvblind
![Page 8: Inferring the kernel: multiscale method Input image Loop over scales Variational Bayes Upsample estimates Use multi-scale approach to avoid local minima:](https://reader035.vdocuments.mx/reader035/viewer/2022070305/551477ea550346b0158b5394/html5/thumbnails/8.jpg)
Original
Our output
Close-up of garland
Matlab’sdeconvblind
![Page 9: Inferring the kernel: multiscale method Input image Loop over scales Variational Bayes Upsample estimates Use multi-scale approach to avoid local minima:](https://reader035.vdocuments.mx/reader035/viewer/2022070305/551477ea550346b0158b5394/html5/thumbnails/9.jpg)
A submitted photograph
A small list of the reasons why we didn’t attempt this photograph:
• Most of the features of interest are saturated.
• Different blur kernels for different lights (compare lantern streaks with sky light streaks and different than the water reflection streaks, and the car streaks below bridge and the streaks to left of bridge.)
• The objects reflected by flash are stationary and have no motion blur.
![Page 10: Inferring the kernel: multiscale method Input image Loop over scales Variational Bayes Upsample estimates Use multi-scale approach to avoid local minima:](https://reader035.vdocuments.mx/reader035/viewer/2022070305/551477ea550346b0158b5394/html5/thumbnails/10.jpg)
We don’t handle subject motion blur
![Page 11: Inferring the kernel: multiscale method Input image Loop over scales Variational Bayes Upsample estimates Use multi-scale approach to avoid local minima:](https://reader035.vdocuments.mx/reader035/viewer/2022070305/551477ea550346b0158b5394/html5/thumbnails/11.jpg)
Failure mode
![Page 12: Inferring the kernel: multiscale method Input image Loop over scales Variational Bayes Upsample estimates Use multi-scale approach to avoid local minima:](https://reader035.vdocuments.mx/reader035/viewer/2022070305/551477ea550346b0158b5394/html5/thumbnails/12.jpg)
Original photograph
![Page 13: Inferring the kernel: multiscale method Input image Loop over scales Variational Bayes Upsample estimates Use multi-scale approach to avoid local minima:](https://reader035.vdocuments.mx/reader035/viewer/2022070305/551477ea550346b0158b5394/html5/thumbnails/13.jpg)
Matlab’s deconvblind
![Page 14: Inferring the kernel: multiscale method Input image Loop over scales Variational Bayes Upsample estimates Use multi-scale approach to avoid local minima:](https://reader035.vdocuments.mx/reader035/viewer/2022070305/551477ea550346b0158b5394/html5/thumbnails/14.jpg)
Photoshop sharpen more
![Page 15: Inferring the kernel: multiscale method Input image Loop over scales Variational Bayes Upsample estimates Use multi-scale approach to avoid local minima:](https://reader035.vdocuments.mx/reader035/viewer/2022070305/551477ea550346b0158b5394/html5/thumbnails/15.jpg)
Our output Blur kernel
![Page 16: Inferring the kernel: multiscale method Input image Loop over scales Variational Bayes Upsample estimates Use multi-scale approach to avoid local minima:](https://reader035.vdocuments.mx/reader035/viewer/2022070305/551477ea550346b0158b5394/html5/thumbnails/16.jpg)
![Page 17: Inferring the kernel: multiscale method Input image Loop over scales Variational Bayes Upsample estimates Use multi-scale approach to avoid local minima:](https://reader035.vdocuments.mx/reader035/viewer/2022070305/551477ea550346b0158b5394/html5/thumbnails/17.jpg)
Original photograph
![Page 18: Inferring the kernel: multiscale method Input image Loop over scales Variational Bayes Upsample estimates Use multi-scale approach to avoid local minima:](https://reader035.vdocuments.mx/reader035/viewer/2022070305/551477ea550346b0158b5394/html5/thumbnails/18.jpg)
Our output
Blur kernel
![Page 19: Inferring the kernel: multiscale method Input image Loop over scales Variational Bayes Upsample estimates Use multi-scale approach to avoid local minima:](https://reader035.vdocuments.mx/reader035/viewer/2022070305/551477ea550346b0158b5394/html5/thumbnails/19.jpg)
Original photograph
![Page 20: Inferring the kernel: multiscale method Input image Loop over scales Variational Bayes Upsample estimates Use multi-scale approach to avoid local minima:](https://reader035.vdocuments.mx/reader035/viewer/2022070305/551477ea550346b0158b5394/html5/thumbnails/20.jpg)
Our output
Blur kernel
![Page 21: Inferring the kernel: multiscale method Input image Loop over scales Variational Bayes Upsample estimates Use multi-scale approach to avoid local minima:](https://reader035.vdocuments.mx/reader035/viewer/2022070305/551477ea550346b0158b5394/html5/thumbnails/21.jpg)
Matlab’s deconvblind
![Page 22: Inferring the kernel: multiscale method Input image Loop over scales Variational Bayes Upsample estimates Use multi-scale approach to avoid local minima:](https://reader035.vdocuments.mx/reader035/viewer/2022070305/551477ea550346b0158b5394/html5/thumbnails/22.jpg)
Original photograph