Image Deblurring Using Dark Channel Prior. Liang Zhang (lzhang432)

Size: px

Start display at page:

Download "Image Deblurring Using Dark Channel Prior. Liang Zhang (lzhang432)"

Deborah Jackson
6 years ago
Views:

1 Image Deblurring Using Dark Channel Prior Liang Zhang (lzhang432)

2 Motivation Solutions Dark Channel Model Optimization Application Future Work Reference Outline

3 Motivation Recover Blur Image Photos are taken everyday (mobile phone, digital camera, GoPros) Blur Images are undesirable Hard to reproduce the capture moment How to get deblur image without have to retake picture? Example of Blur Image

4 Motivation Blur Image Clear Image Blur Kernel Noise Blur Image = Sharp Image * Blur Kernel + Noise[8]

5 Motivation Blur Image Clear Image Blur Kernel Noise Blur Image = Sharp Image * Blur Kernel + Noise[8]

6 Motivation Solutions Dark Channel Model Optimization Application Future Work Reference Outline

7 Convolution Convolution: Weighted average of a patch /9 1/9 1/9 1/9 1/9 1/9 1/9 1/9 1/9 Blur Kernel Clear Image

8 Convolution Convolution: Weighted average of a patch /9 1/9 1/9 1/9 1/9 1/9 1/9 1/9 1/9 Blur Kernel 45 Clear Image

9 Convolution Convolution: Weighted average of a patch Dark Channel: The lowest value among a patch /9 1/9 1/9 1/9 1/9 1/9 1/9 1/9 1/9 Blur Kernel 45 >= 0 Clear Image

10 Convolution and Dark Channel Dark Channel Image Dark channel of blurred image are less sparse than the dark channel of sharp image Clear Image Blurred Image

11 Deblur Approach Dark Channel Image Clear Image Blurred Image

12 Motivation Solutions Dark Channel Model Optimization Application Future Work Reference Outline

13 Model Based of fact that the dark channel of sharp image have more number of zerointensity pixels [8]

14 Model Based of fact that the dark channel of sharp image have more number of zerointensity pixels [8] Data Fitting

15 Model Based of fact that the dark channel of sharp image have more number of zerointensity pixels Blur Kernel Regulari zation [8]

16 Model Based of fact that the dark channel of sharp image have more number of zerointensity pixels Gradients of Image Sparsity [8]

17 Model Based of fact that the dark channel of sharp image have more number of zerointensity pixels [8] L0 norm Nonlinear min operator This term is used to measure the sparsity of dark channel

18 Non-linear Operation D(I) = MI [8] D(I): vectorized of D(I) M: indicator matrix of dark channel I: vectorized latent image M Latent Image Dark Channel

19 Non-linear Operation D(I) = MI [8] D(I): vectorized of D(I) M: indicator matrix of dark channel I: vectorized latent image M Latent Image Dark Channel

20 Non-linear Operation D(I) = MI [8] D(I): vectorized of D(I) M: indicator matrix of dark channel I: vectorized latent image M Latent Image Dark Channel

21 Blur Kernel and Clear Image Dark Channel of Latent Image Blur Kernel Clear Image

22 Motivation Solutions Dark Channel Model Optimization Application Future Work Reference Outline

23 Application Run with paper s data set

24 Application Run with paper s data set

25 Application Run with our own data set (blur images are download from google)

26 Motivation Solutions Dark Channel Model Optimization Application Future Work Reference Outline

27 Future Work Parallel computing implementation to accelerate deblur computing Implement the dark channel on mobile phone Improve the dark channel methods

28 Motivation Solutions Dark Channel Model Optimization Application Future Work Reference Outline

29 Reference [1] L.B.Lucy. An iterative technique for the rectification of observed distributions. Astronomy Journal, 79(6): , [2] T, Chan anc C.Wong. Total variation blind deconvolution.. IEEE TIP, 7(3): , [3] R.Fergus, B.Singh, A.Hertzmann, S.T.Roweis, and W.T.Freeman. Removing camera shake from a single photograph. ACM SIGGRAPH, 25(3): , 2006.

30 Reference [4] Y.Hacohen, E. Shechtman, and D.Lischinski. Deblurring by example using dense correspondence. In ICCV, pages , 2013 [5] D.Krishnan, T.Tay, and R.Fergus. Blind deconvolution using a normalized sparsit measure. In CVPR, pages , 2011 [6] T.Michaeli and M.Irani Blind deblurring using internal patch recurrence. In ECCV, pages , 2014

31 Reference [7] K.He, J.Sun, and X.Tang Single image haze removal using dark channel prior. In CVPR, pages , 2009 [8] Jinshan Pan, Deqing Sun, Hanspeter Pfister, and Ming-Hsuan Yang Blind Image Deblurring Using Dark Channel Prior. In CVPR, 2016 [9] [10] [11] q=blur+image&espv=2&source=lnms&tbm=isch&sa=x&ved=0ahukew jfntk7vrztahuo_imkhrnfam4q_auibigb&biw=1074&bih=709&dpr=1

32 Thanks

33 Q & A

34 Backup slides

CS766 Project Mid-Term Report Blind Image Deblurring

CS766 Project Mid-Term Report Blind Image Deblurring Liang Zhang (lzhang432) April 7, 2017 1 Summary I stickly follow the project timeline. At this time, I finish the main body the image deblurring, and