Blind Image Deblurring Using Dark Channel Prior

Size: px
Start display at page:

Download "Blind Image Deblurring Using Dark Channel Prior"

Transcription

1 Blind Image Deblurring Using Dark Channel Prior Jinshan Pan 1,2,3, Deqing Sun 2,4, Hanspeter Pfister 2, and Ming-Hsuan Yang 3 1 Dalian University of Technology 2 Harvard University 3 UC Merced 4 NVIDIA

2 Overview Blurred image captured in low-light conditions 2

3 Overview Restored image 3

4 Overview Blurred image 4

5 Overview Restored image 5

6 Overview Our goal A generic method state-of-the-art performance on natural images great results on specific scenes (e.g. saturated images, text images, face images) No edge selection for natural image deblurring No engineering efforts to incorporate domain knowledge for specific scenario deblurring 6

7 Blur Process Blur is uniform and spatially invariant Blurred image Sharp image Blur kernel Noise 7

8 Blur Process Blur is uniform and spatially invariant Blurred image Sharp image Blur kernel Noise Convolution operator 8

9 Challenging Blind image deblurring is challenging?? 9

10 Ill-Posed Problem 10

11 Ill-Posed Problem 11

12 Related Work Probabilistic approach Posterior distribution Likelihood Prior on I Prior on k p k, I B p B I, k p I p k Blur kernel k Latent image I Blurred image B 12

13 Related Work Blur kernel prior Positive and sparse Most elements near zero P(k) p(b) A few can be large 10 Shan et al., SIGGRAPH k b 13

14 Related Work Sharp image statistics Fergus et al., SIGGRAPH 2006, Levin et al, CVPR 2009, Shan et al., SIGGRAPH 2008 Histogram of image gradients Log # pixels 14

15 Related Work Gaussian: -I 2 Log prob - I 0.5 Laplacian: - I - I 0.25 I I Parametric models Derivative distributions in natural images are sparse: log pi ( ) = I α i, α < 1 Levin et al., SIGGRAPH 2007, CVPR 2009 i 15

16 Related Work MAP I,k framework p k, I B p B I, k p I p k argmax k,i p k, I B (I, k) = argmin k,i {l B I k + φ I + φ k } 16

17 Related Work The MAP I,k paradox [Levin et al., CVPR 2009] P(, )>P(, ) Latent image kernel Latent image kernel 17

18 Related Work The MAP I,k paradox [Levin et al., CVPR 2009] sharp blurred i α <? 18 i α

19 Related Work The MAP I,k paradox [Levin et al., CVPR 2009] 15x15 windows 25x25 windows 45x45 windows simple derivatives [-1,1],[-1;1] FoE filters (Roth&Black) Red windows = [ p(sharp I) >p(blurred I) ] 19

20 Related Work The MAP I,k paradox [Levin et al., CVPR 2009] P(step edge) d = 1 < k=[0.5,0.5] P(blurred step edge) d1 = 0.5 d2 = 0.5 sum of derivatives: cheaper 0 = = P(impulse) < P(blurred impulse) sum of derivatives: d =1 1 1 d 2 = d = 0.5 d = = = cheaper 20

21 Related Work The MAP I,k paradox [Levin et al., CVPR 2009] P(sharp real image) < P(blurred real image) 0.5 I i i = I i i = 4.5 cheaper Noise and texture behave as impulses - total derivative contrast reduced by blur 21

22 Related Work The MAP I,k paradox [Levin et al., CVPR 2009] Maximum marginal probability estimation Marginalized probability [Levin et al., CVPR 2011] Variational Bayesian [Fergus et al., SIGGRAPH 2006] MAP I,k p k B p B k p k = p B, I k p k di I = p B I, k p(i)p k di l p k, I B p B I, k p(i)p k Marginalizing over I 22

23 Related Work The MAP I,k paradox [Levin et al., CVPR 2009] Maximum marginal probability estimation Marginalized probability [Levin et al., CVPR 2011] Variational Bayesian [Fergus et al., SIGGRAPH 2006] Score Optimization surface for a single variable Maximum a-posteriori (MAP) Variational Bayes Pixel intensity Computationally expensive 23

24 Related Work Priors favor clear images [Krishnan et al., CVPR 2011, Pan et al., CVPR 2014, Michaeli and Irani, ECCV 2014] E(Clear image) < E(Blurred image) Effective for some specific images, such as natural images or text images Cannot be generalized well 24

25 Related Work MAP I,k with Edge Selection Main idea E(clear) < E(blurred) in sharp edge regions [Levin et al., CVPR 2009] [Cho and Lee SIGGRAPH Asia 2009, Xu and Jia ECCV 2010, ] Advantages and Limitations Fast and effective in practice Explicitly try to recover sharp edges using heuristic image filters and usually fail when sharp edges are not available 25

26 Related Work MAP I,k with Edge Selection (Extension) Exemplar based methods [Sun et al., ICCP 2013, HaCohen et al., ICCV 2013, Pan et al., ECCV 2014] Computationally expensive 26

27 Our Work Dark channel prior Theoretical analysis Efficient numerical solver Applications 27

28 Convolution and Dark Channel Dark channel [He et al., CVPR 2009] c DI ( )( x) = min I( y) y N( x) c { rgb,, } Compute the minimum intensity in a patch of an image 28

29 Convolution and Dark Channel Convolution s B(x) = I(x+[ ] - z) k(z) 2 z Ω k Ω k: the domain of blur kernel s : the size of blur kernel [ ] : the rounding operator k(z) 0, k(z)=1 z Ω k 29

30 Convolution and Dark Channel Proposition 1: Let N(x) denote a patch centered at pixel x with size the same as the blur kernel. We have: B(x) min I(y) y N(x) /9 1/9 1/9 1/9 1/9 1/9 1/9 1/9 1/ A toy example 30

31 Convolution and Dark Channel Property 1: Let D(B) and D(I) denote the dark channel of the blurred and clear images, we have: D( B)(x) D( I)(x) Property 2: Let Ω denote the domain of an image I. If there exist some pixels x Ω such that I(x) = 0, we have: D( B) > D( I)

32 Convolution and Dark Channel Average number of dark pixels Blurred images Clear images Intensity The statistical results on the dataset with 3,200 examples 32

33 Convolution and Dark Channel Clear Blurred Clear Blurred Blurred images have less sparse dark channels than clear images 33

34 Proposed Method Our model Add the dark channel prior into standard deblurring model min I* k B + γ k + µ I + λ DI ( ) Ik, How to solve? L0 norm and non-linear min operator 34

35 Optimization Algorithm skeleton min I* k B +γ k k L0 norm min I* k B + µ I + λ DI ( ) I Half-quadratic splitting method Non-linear min operator Linear approximation

36 Optimization Update latent image I: min I * k B + µ I + λ DI ( ) I Half-quadratic splitting [Xu et al., SIGGRAPH Asia 2011, Pan et al., CVPR 2014] min I* k B + α I g + β DI ( ) u + µ g + λ u Iug,, 2 2 Alternative minimization min I* k B + β DI ( ) u + µ I g I min α β µ λ ug, 2 2 I g + DI ( ) u + g 0 + u 0 36

37 Optimization Update latent image I: u, g sub-problem α I g β DI u + µ g + λ u 2 2 min + ( ) 0 0 ug, + 2 min β DI ( ) u λ u 0 u 2 min α x g + µ g 0 g u and g are independent! u 2 2 DI ( ), DI ( ) = β g 0, otherwise λ µ I, I = α 0, otherwise Related papers: [Xu et al., SIGGRAPH Asia 2011, Xu et al., CVPR 2013, Pan et al., CVPR 2014] 37

38 Optimization Update latent image I: I sub-problem min operator min I* k B + β DI ( ) u + µ I g I Our observation DI ( )=MI Let y = argmin z N x I(z), we have 1, z=y, M(x, z)= 0, otherwise. 38

39 Optimization I sub-problem Compute M M Intermediate image I D(I) M T Visualization of M T u u Toy example 39

40 Experimental Results Natural image deblurring Specific scenes Text images Face images Low-light images Non-uniform image deblurring 40

41 Natural Image Deblurring Results Quantitative evaluation Levin et al., CVPR 2009 Köhler et al. ECCV 2012 Sun et al., ICCP

42 Natural Image Deblurring Results % Success rate (%) Ours 80 Xu et al. Xu and Jia 60 Pan et al. Levin et al. 40 Cho and Lee Michaeli and Irani Krishnan et al Error ratios Quantitative evaluations on the dataset by Levin et al., CVPR

43 Natural Image Deblurring Results Average PSNR Values im01 im02 im03 im04 Average Blurred images Fergus et al. Shan et al. Cho and Lee Xu and Jia Krishnan et al. Hirsch et al. Whyte et al. Pan et al. Ours Quantitative evaluations on the dataset by Köhler et al. ECCV

44 Natural Image Deblurring Results Success rate (%) Error ratios Ours Xu and Jia Pan et al. Michaeli and Irani Sun et al. Xu et al. Levin et al. Krishnan et al. Cho and Lee Quantitative evaluations on the dataset by Sun et al. ICCP

45 Natural Image Deblurring Results Blurred image Cho and Lee SIGGRAPH Asia 2009 Xu and Jia, ECCV 2010 Krishnan et al., CVPR 2011 Ours without D(I) Ours 45

46 Natural Image Deblurring Results Blurred image Krishnan et al., CVPR 2011 Xu et al., CVPR 2013 Pan et al., CVPR 2014 Ours without D(I) Ours Our real captured example 46

47 Text Image Deblurring Results Average PSNRs Cho and Lee Xu and Jia Krishnan et al Levin et al Xu et al Pan et al Ours Natural image debluring methods Quantitative evaluations on the text image dataset by Pan et al., CVPR

48 Text Image Deblurring Results Blurred image Xu et al., CVPR 2013 Pan et al., CVPR 2014 Real captured example Ours 48

49 Saturated Image Deblurring Results Blurred image Xu et al., CVPR 2013 Pan et al., CVPR 2014 Real captured example Ours 49

50 Face Image Deblurring Results Blurred image Xu et al., CVPR 2013 Pan et al., ECCV 2014 Ours Real captured example 50

51 Non-Uniform Deblurring Blurred image Krishnan et al., CVPR 2011 Whyte et al., IJCV 2012 Xu et al., CVPR 2013 Ours Our estimated kernels 51

52 Convergence Average Kernel Similarity Average Energies Iterations Iterations Kernel similarity plot Objective function value plot 52

53 Running Time Running time (/s) comparisons (obtained on the same PC). Method 255 x x x 800 Xu et al. (C++) Krishnan et al. (Matlab) Levin et al. (Matlab) Ours without D(I) (Matlab) Ours with naive implementation (Matlab) Ours (Matlab)

54 Analysis and Discussions Effectiveness of dark channel prior Average PSNR Values Ours without dark channel Ours im01 im02 im03 im04 Average Results on the dataset by Köhler et al. ECCV 2012 Success rate (%) Ours without dark channel Error ratios Ours Results on the dataset by Levin et al. CVPR

55 Analysis and Discussions Existing prior favors clear images [Krishnan et al. CVPR 2011] Energy Values of p(i) I pi ( ) = I Image index 1 2 Blurred images Clear images Statistics of different priors on the text image deblurring by Pan et al., CVPR The normalized sparsity sometimes favors blurred text images 55

56 Analysis and Discussions Dark channel prior favors clear images Average number of dark pixels Blurred images Clear images Intensity Statistics of different priors on the text image deblurring by Pan et al., CVPR The dark channel prior favors clear text images 56

57 Limitations The dark channel of clear image does not contain zero-elements DB ( ) = DI ( ) 0 0 Property 2 does not hold Dark channel prior has no effect on image deblurring 57

58 Limitations The dark channel of clear image does not contain zero-elements Blurred image Without D(I) Ours Dark channel of clear image Dark channel of blurred image Estimated dark channel Dark channel prior has no effect on image deblurring 58

59 Limitations Images containing noise Blurred image 59

60 Limitations Images containing noise Without D(I) 60

61 Limitations Images containing noise With D(I) 61

62 Take Home Message The change in the sparsity of the dark channel is an inherent property of the blur process! Code and datasets will be available at the authors websites. 62

63 More Results Real captured image 63

64 More Results Our result 64

65 More Results Real captured image 65

66 More Results Our result 66

67 Our Related Deblurring Work Outlier deblurring (CVPR 2016) er-deblur/ Object motion deblurring (CVPR 2016) ct-deblur/ Text image deblurring and beyond (TPAMI 2016) 67

Deblurring Text Images via L 0 -Regularized Intensity and Gradient Prior

Deblurring Text Images via L 0 -Regularized Intensity and Gradient Prior Deblurring Text Images via L -Regularized Intensity and Gradient Prior Jinshan Pan, Zhe Hu, Zhixun Su, Ming-Hsuan Yang School of Mathematical Sciences, Dalian University of Technology Electrical Engineering

More information

Learning Data Terms for Non-blind Deblurring Supplemental Material

Learning Data Terms for Non-blind Deblurring Supplemental Material Learning Data Terms for Non-blind Deblurring Supplemental Material Jiangxin Dong 1, Jinshan Pan 2, Deqing Sun 3, Zhixun Su 1,4, and Ming-Hsuan Yang 5 1 Dalian University of Technology dongjxjx@gmail.com,

More information

Robust Kernel Estimation with Outliers Handling for Image Deblurring

Robust Kernel Estimation with Outliers Handling for Image Deblurring Robust Kernel Estimation with Outliers Handling for Image Deblurring Jinshan Pan,, Zhouchen Lin,4,, Zhixun Su,, and Ming-Hsuan Yang School of Mathematical Sciences, Dalian University of Technology Electrical

More information

Blind Deblurring using Internal Patch Recurrence. Tomer Michaeli & Michal Irani Weizmann Institute

Blind Deblurring using Internal Patch Recurrence. Tomer Michaeli & Michal Irani Weizmann Institute Blind Deblurring using Internal Patch Recurrence Tomer Michaeli & Michal Irani Weizmann Institute Scale Invariance in Natural Images Small patterns recur at different scales Scale Invariance in Natural

More information

Deblurring Face Images with Exemplars

Deblurring Face Images with Exemplars Deblurring Face Images with Exemplars Jinshan Pan 1, Zhe Hu 2, Zhixun Su 1, and Ming-Hsuan Yang 2 1 Dalian University of Technology 2 University of California at Merced Abstract. The human face is one

More information

Digital Image Restoration

Digital Image Restoration Digital Image Restoration Blur as a chance and not a nuisance Filip Šroubek sroubekf@utia.cas.cz www.utia.cas.cz Institute of Information Theory and Automation Academy of Sciences of the Czech Republic

More information

Learning Data Terms for Non-blind Deblurring

Learning Data Terms for Non-blind Deblurring Learning Data Terms for Non-blind Deblurring Jiangxin Dong 1, Jinshan Pan 2, Deqing Sun 3, Zhixun Su 1,4, and Ming-Hsuan Yang 5 1 Dalian University of Technology dongjxjx@gmail.com, zxsu@dlut.edu.com 2

More information

Robust Kernel Estimation with Outliers Handling for Image Deblurring

Robust Kernel Estimation with Outliers Handling for Image Deblurring Robust Kernel Estimation with Outliers Handling for Image Deblurring Jinshan Pan,2, Zhouchen Lin 3,4,, Zhixun Su,5, and Ming-Hsuan Yang 2 School of Mathematical Sciences, Dalian University of Technology

More information

Learning Fully Convolutional Networks for Iterative Non-blind Deconvolution

Learning Fully Convolutional Networks for Iterative Non-blind Deconvolution Learning Fully Convolutional Networks for Iterative Non-blind Deconvolution Jiawei Zhang 13 Jinshan Pan 2 Wei-Sheng Lai 3 Rynson W.H. Lau 1 Ming-Hsuan Yang 3 Department of Computer Science, City University

More information

Learning a Discriminative Prior for Blind Image Deblurring

Learning a Discriminative Prior for Blind Image Deblurring Learning a Discriative Prior for Blind Image Deblurring tackle this problem, additional constraints and prior knowledge on both blur kernels and images are required. The main success of the recent deblurring

More information

A Comparative Study for Single Image Blind Deblurring

A Comparative Study for Single Image Blind Deblurring A Comparative Study for Single Image Blind Deblurring Wei-Sheng Lai Jia-Bin Huang Zhe Hu Narendra Ahuja Ming-Hsuan Yang University of California, Merced University of Illinois, Urbana-Champaign http://vllab.ucmerced.edu/

More information

Joint Depth Estimation and Camera Shake Removal from Single Blurry Image

Joint Depth Estimation and Camera Shake Removal from Single Blurry Image Joint Depth Estimation and Camera Shake Removal from Single Blurry Image Zhe Hu1 Li Xu2 Ming-Hsuan Yang1 1 University of California, Merced 2 Image and Visual Computing Lab, Lenovo R & T zhu@ucmerced.edu,

More information

Deblurring by Example using Dense Correspondence

Deblurring by Example using Dense Correspondence 2013 IEEE International Conference on Computer Vision Deblurring by Example using Dense Correspondence Yoav HaCohen Hebrew University Jerusalem, Israel yoav.hacohen@mail.huji.ac.il Eli Shechtman Adobe

More information

Good Regions to Deblur

Good Regions to Deblur Good Regions to Deblur Zhe Hu and Ming-Hsuan Yang Electrical Engineering and Computer Science University of California at Merced {zhu, mhyang}@ucmerced.edu Abstract. The goal of single image deblurring

More information

Edge-Based Blur Kernel Estimation Using Sparse Representation and Self-Similarity

Edge-Based Blur Kernel Estimation Using Sparse Representation and Self-Similarity Noname manuscript No. (will be inserted by the editor) Edge-Based Blur Kernel Estimation Using Sparse Representation and Self-Similarity Jing Yu Zhenchun Chang Chuangbai Xiao Received: date / Accepted:

More information

arxiv: v2 [cs.cv] 1 Aug 2016

arxiv: v2 [cs.cv] 1 Aug 2016 A Neural Approach to Blind Motion Deblurring arxiv:1603.04771v2 [cs.cv] 1 Aug 2016 Ayan Chakrabarti Toyota Technological Institute at Chicago ayanc@ttic.edu Abstract. We present a new method for blind

More information

BLIND IMAGE DEBLURRING VIA REWEIGHTED GRAPH TOTAL VARIATION

BLIND IMAGE DEBLURRING VIA REWEIGHTED GRAPH TOTAL VARIATION BLIND IMAGE DEBLURRING VIA REWEIGHTED GRAPH TOTAL VARIATION Yuanchao Bai, Gene Cheung, Xianming Liu $, Wen Gao Peking University, Beijing, China, $ Harbin Institute of Technology, Harbin, China National

More information

Normalized Blind Deconvolution

Normalized Blind Deconvolution Normalized Blind Deconvolution Meiguang Jin 1[0000 0003 3796 2310], Stefan Roth 2[0000 0001 9002 9832], and Paolo Favaro 1[0000 0003 3546 8247] 1 University of Bern, Switzerland 2 TU Darmstadt, Germany

More information

Robust Single Image Super-resolution based on Gradient Enhancement

Robust Single Image Super-resolution based on Gradient Enhancement Robust Single Image Super-resolution based on Gradient Enhancement Licheng Yu, Hongteng Xu, Yi Xu and Xiaokang Yang Department of Electronic Engineering, Shanghai Jiaotong University, Shanghai 200240,

More information

Self-paced Kernel Estimation for Robust Blind Image Deblurring

Self-paced Kernel Estimation for Robust Blind Image Deblurring Self-paced Kernel Estimation for Robust Blind Image Deblurring Dong Gong, Mingkui Tan, Yanning Zhang, Anton van den Hengel, Qinfeng Shi School of Computer Science and Engineering, Northwestern Polytechnical

More information

Structured Face Hallucination

Structured Face Hallucination 2013 IEEE Conference on Computer Vision and Pattern Recognition Structured Face Hallucination Chih-Yuan Yang Sifei Liu Ming-Hsuan Yang Electrical Engineering and Computer Science University of California

More information

1510 IEEE TRANSACTIONS ON MULTIMEDIA, VOL. 16, NO. 6, OCTOBER Efficient Patch-Wise Non-Uniform Deblurring for a Single Image

1510 IEEE TRANSACTIONS ON MULTIMEDIA, VOL. 16, NO. 6, OCTOBER Efficient Patch-Wise Non-Uniform Deblurring for a Single Image 1510 IEEE TRANSACTIONS ON MULTIMEDIA, VOL. 16, NO. 6, OCTOBER 2014 Efficient Patch-Wise Non-Uniform Deblurring for a Single Image Xin Yu, Feng Xu, Shunli Zhang, and Li Zhang Abstract In this paper, we

More information

Patch Mosaic for Fast Motion Deblurring

Patch Mosaic for Fast Motion Deblurring Patch Mosaic for Fast Motion Deblurring Hyeoungho Bae, 1 Charless C. Fowlkes, 2 and Pai H. Chou 1 1 EECS Department, University of California, Irvine 2 Computer Science Department, University of California,

More information

Single Image Deblurring Using Motion Density Functions

Single Image Deblurring Using Motion Density Functions Single Image Deblurring Using Motion Density Functions Ankit Gupta 1, Neel Joshi 2, C. Lawrence Zitnick 2, Michael Cohen 2, and Brian Curless 1 1 University of Washington 2 Microsoft Research Abstract.

More information

Deblurring Shaken and Partially Saturated Images

Deblurring Shaken and Partially Saturated Images Deblurring Shaken and Partially Saturated Images Oliver Whyte, INRIA Josef Sivic, Andrew Zisserman,, Ecole Normale Supe rieure Dept. of Engineering Science University of Oxford Abstract We address the

More information

State-of-the-Art Image Motion Deblurring Technique

State-of-the-Art Image Motion Deblurring Technique State-of-the-Art Image Motion Deblurring Technique Hang Qiu 5090309140 Shanghai Jiao Tong University qhqd0708sl@gmail.com Abstract In this paper, image motion deblurring technique is widely surveyed and

More information

arxiv: v1 [cs.cv] 11 Aug 2017

arxiv: v1 [cs.cv] 11 Aug 2017 Video Deblurring via Semantic Segmentation and Pixel-Wise Non-Linear Kernel arxiv:1708.03423v1 [cs.cv] 11 Aug 2017 Wenqi Ren 1,2, Jinshan Pan 3, Xiaochun Cao 1,4, and Ming-Hsuan Yang 5 1 State Key Laboratory

More information

Non-blind Deblurring: Handling Kernel Uncertainty with CNNs

Non-blind Deblurring: Handling Kernel Uncertainty with CNNs Non-blind Deblurring: Handling Kernel Uncertainty with CNNs Subeesh Vasu 1, Venkatesh Reddy Maligireddy 2, A. N. Rajagopalan 3 Indian Institute of Technology Madras subeeshvasu@gmail.com 1, venkateshmalgireddy@gmail.com

More information

Computer Vision I - Algorithms and Applications: Basics of Image Processing

Computer Vision I - Algorithms and Applications: Basics of Image Processing Computer Vision I - Algorithms and Applications: Basics of Image Processing Carsten Rother 28/10/2013 Computer Vision I: Basics of Image Processing Link to lectures Computer Vision I: Basics of Image Processing

More information

Guided Image Super-Resolution: A New Technique for Photogeometric Super-Resolution in Hybrid 3-D Range Imaging

Guided Image Super-Resolution: A New Technique for Photogeometric Super-Resolution in Hybrid 3-D Range Imaging Guided Image Super-Resolution: A New Technique for Photogeometric Super-Resolution in Hybrid 3-D Range Imaging Florin C. Ghesu 1, Thomas Köhler 1,2, Sven Haase 1, Joachim Hornegger 1,2 04.09.2014 1 Pattern

More information

Kernel Fusion for Better Image Deblurring

Kernel Fusion for Better Image Deblurring Kernel Fusion for Better Image Deblurring Long Mai Portland State University mtlong@cs.pdx.edu Feng Liu Portland State University fliu@cs.pdx.edu Abstract Kernel estimation for image deblurring is a challenging

More information

Removing Atmospheric Turbulence

Removing Atmospheric Turbulence Removing Atmospheric Turbulence Xiang Zhu, Peyman Milanfar EE Department University of California, Santa Cruz SIAM Imaging Science, May 20 th, 2012 1 What is the Problem? time 2 Atmospheric Turbulence

More information

Image Denoising and Blind Deconvolution by Non-uniform Method

Image Denoising and Blind Deconvolution by Non-uniform Method Image Denoising and Blind Deconvolution by Non-uniform Method B.Kalaiyarasi 1, S.Kalpana 2 II-M.E(CS) 1, AP / ECE 2, Dhanalakshmi Srinivasan Engineering College, Perambalur. Abstract Image processing allows

More information

Optimal Denoising of Natural Images and their Multiscale Geometry and Density

Optimal Denoising of Natural Images and their Multiscale Geometry and Density Optimal Denoising of Natural Images and their Multiscale Geometry and Density Department of Computer Science and Applied Mathematics Weizmann Institute of Science, Israel. Joint work with Anat Levin (WIS),

More information

Computer Vision I - Filtering and Feature detection

Computer Vision I - Filtering and Feature detection Computer Vision I - Filtering and Feature detection Carsten Rother 30/10/2015 Computer Vision I: Basics of Image Processing Roadmap: Basics of Digital Image Processing Computer Vision I: Basics of Image

More information

Blind Deconvolution with Non-local Sparsity Reweighting

Blind Deconvolution with Non-local Sparsity Reweighting Blind Deconvolution with Non-local Sparsity Reweighting arxiv:1311.4029v2 [cs.cv] 16 Jun 2014 Dilip Krishnan 1, Joan Bruna 2 and Rob Fergus 2,3 1 : CSAIL, Massachussetts Institute of Technology 2 : Courant

More information

IMAGE DENOISING TO ESTIMATE THE GRADIENT HISTOGRAM PRESERVATION USING VARIOUS ALGORITHMS

IMAGE DENOISING TO ESTIMATE THE GRADIENT HISTOGRAM PRESERVATION USING VARIOUS ALGORITHMS IMAGE DENOISING TO ESTIMATE THE GRADIENT HISTOGRAM PRESERVATION USING VARIOUS ALGORITHMS P.Mahalakshmi 1, J.Muthulakshmi 2, S.Kannadhasan 3 1,2 U.G Student, 3 Assistant Professor, Department of Electronics

More information

Author(s): Title: Journal: ISSN: Year: 2014 Pages: Volume: 25 Issue: 5

Author(s): Title: Journal: ISSN: Year: 2014 Pages: Volume: 25 Issue: 5 Author(s): Ming Yin, Junbin Gao, David Tien, Shuting Cai Title: Blind image deblurring via coupled sparse representation Journal: Journal of Visual Communication and Image Representation ISSN: 1047-3203

More information

Image Restoration with Deep Generative Models

Image Restoration with Deep Generative Models Image Restoration with Deep Generative Models Raymond A. Yeh *, Teck-Yian Lim *, Chen Chen, Alexander G. Schwing, Mark Hasegawa-Johnson, Minh N. Do Department of Electrical and Computer Engineering, University

More information

Image Segmentation Using Iterated Graph Cuts Based on Multi-scale Smoothing

Image Segmentation Using Iterated Graph Cuts Based on Multi-scale Smoothing Image Segmentation Using Iterated Graph Cuts Based on Multi-scale Smoothing Tomoyuki Nagahashi 1, Hironobu Fujiyoshi 1, and Takeo Kanade 2 1 Dept. of Computer Science, Chubu University. Matsumoto 1200,

More information

Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform. Xintao Wang Ke Yu Chao Dong Chen Change Loy

Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform. Xintao Wang Ke Yu Chao Dong Chen Change Loy Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform Xintao Wang Ke Yu Chao Dong Chen Change Loy Problem enlarge 4 times Low-resolution image High-resolution image Previous

More information

IMAGE RESTORATION VIA EFFICIENT GAUSSIAN MIXTURE MODEL LEARNING

IMAGE RESTORATION VIA EFFICIENT GAUSSIAN MIXTURE MODEL LEARNING IMAGE RESTORATION VIA EFFICIENT GAUSSIAN MIXTURE MODEL LEARNING Jianzhou Feng Li Song Xiaog Huo Xiaokang Yang Wenjun Zhang Shanghai Digital Media Processing Transmission Key Lab, Shanghai Jiaotong University

More information

Single Image Motion Deblurring Using Transparency

Single Image Motion Deblurring Using Transparency Single Image Motion Deblurring Using Transparency Jiaya Jia Department of Computer Science and Engineering The Chinese University of Hong Kong leojia@cse.cuhk.edu.hk Abstract One of the key problems of

More information

Image deconvolution using a characterization of sharp images in wavelet domain

Image deconvolution using a characterization of sharp images in wavelet domain Image deconvolution using a characterization of sharp images in wavelet domain Hui Ji a,, Jia Li a, Zuowei Shen a, Kang Wang a a Department of Mathematics, National University of Singapore, Singapore,

More information

An improved non-blind image deblurring methods based on FoEs

An improved non-blind image deblurring methods based on FoEs An improved non-blind image deblurring methods based on FoEs Qidan Zhu, Lei Sun College of Automation, Harbin Engineering University, Harbin, 5000, China ABSTRACT Traditional non-blind image deblurring

More information

Efficient 3D Kernel Estimation for Non-uniform Camera Shake Removal Using Perpendicular Camera System

Efficient 3D Kernel Estimation for Non-uniform Camera Shake Removal Using Perpendicular Camera System Efficient 3D Kernel Estimation for Non-uniform Camera Shake Removal Using Perpendicular Camera System Tao Yue yue-t09@mails.tsinghua.edu.cn Jinli Suo Qionghai Dai {jlsuo, qhdai}@tsinghua.edu.cn Department

More information

KERNEL-FREE VIDEO DEBLURRING VIA SYNTHESIS. Feitong Tan, Shuaicheng Liu, Liaoyuan Zeng, Bing Zeng

KERNEL-FREE VIDEO DEBLURRING VIA SYNTHESIS. Feitong Tan, Shuaicheng Liu, Liaoyuan Zeng, Bing Zeng KERNEL-FREE VIDEO DEBLURRING VIA SYNTHESIS Feitong Tan, Shuaicheng Liu, Liaoyuan Zeng, Bing Zeng School of Electronic Engineering University of Electronic Science and Technology of China, Chengdu, China

More information

Blind Deconvolution Using a Normalized Sparsity Measure

Blind Deconvolution Using a Normalized Sparsity Measure Blind Deconvolution Using a Normalized Sparsity Measure Dilip Krishnan Courant Institute New York University dilip@cs.nyu.edu Terence Tay Chatham Digital ttay@chathamdigital.com Rob Fergus Courant Institute

More information

Two-Phase Kernel Estimation for Robust Motion Deblurring

Two-Phase Kernel Estimation for Robust Motion Deblurring Two-Phase Kernel Estimation for Robust Motion Deblurring Li Xu and Jiaya Jia Department of Computer Science and Engineering The Chinese University of Hong Kong {xuli,leojia}@cse.cuhk.edu.hk Abstract. We

More information

Problem Set 4. Assigned: March 23, 2006 Due: April 17, (6.882) Belief Propagation for Segmentation

Problem Set 4. Assigned: March 23, 2006 Due: April 17, (6.882) Belief Propagation for Segmentation 6.098/6.882 Computational Photography 1 Problem Set 4 Assigned: March 23, 2006 Due: April 17, 2006 Problem 1 (6.882) Belief Propagation for Segmentation In this problem you will set-up a Markov Random

More information

The SIFT (Scale Invariant Feature

The SIFT (Scale Invariant Feature The SIFT (Scale Invariant Feature Transform) Detector and Descriptor developed by David Lowe University of British Columbia Initial paper ICCV 1999 Newer journal paper IJCV 2004 Review: Matt Brown s Canonical

More information

Computer Vision I - Basics of Image Processing Part 1

Computer Vision I - Basics of Image Processing Part 1 Computer Vision I - Basics of Image Processing Part 1 Carsten Rother 28/10/2014 Computer Vision I: Basics of Image Processing Link to lectures Computer Vision I: Basics of Image Processing 28/10/2014 2

More information

Single Image Super-resolution. Slides from Libin Geoffrey Sun and James Hays

Single Image Super-resolution. Slides from Libin Geoffrey Sun and James Hays Single Image Super-resolution Slides from Libin Geoffrey Sun and James Hays Cs129 Computational Photography James Hays, Brown, fall 2012 Types of Super-resolution Multi-image (sub-pixel registration) Single-image

More information

Image Segmentation Using Iterated Graph Cuts BasedonMulti-scaleSmoothing

Image Segmentation Using Iterated Graph Cuts BasedonMulti-scaleSmoothing Image Segmentation Using Iterated Graph Cuts BasedonMulti-scaleSmoothing Tomoyuki Nagahashi 1, Hironobu Fujiyoshi 1, and Takeo Kanade 2 1 Dept. of Computer Science, Chubu University. Matsumoto 1200, Kasugai,

More information

From local to global: Edge profiles to camera motion in blurred images

From local to global: Edge profiles to camera motion in blurred images From local to global: Edge profiles to camera motion in blurred images Subeesh Vasu 1, A. N. Rajagopalan 2 Indian Institute of Technology Madras subeeshvasu@gmail.com 1, raju@ee.iitm.ac.in 2 Abstract In

More information

Image Deblurring and Denoising using Color Priors

Image Deblurring and Denoising using Color Priors Image Deblurring and Denoising using Color Priors Neel Joshi C. Lawrence Zitnick Richard Szeliski David J. Kriegman Microsoft Research University of California, San Diego Abstract Image blur and noise

More information

Previously. Part-based and local feature models for generic object recognition. Bag-of-words model 4/20/2011

Previously. Part-based and local feature models for generic object recognition. Bag-of-words model 4/20/2011 Previously Part-based and local feature models for generic object recognition Wed, April 20 UT-Austin Discriminative classifiers Boosting Nearest neighbors Support vector machines Useful for object recognition

More information

TEXT documents such as advertisements, receipts, and

TEXT documents such as advertisements, receipts, and IEEE TRANSACTIONS ON CYBERNETICS 1 Text Image Deblurring Using Kernel Sparsity Prior Xianyong Fang, Member, IEEE, Qiang Zhou, Jianbing Shen, Senior Member, IEEE, Christian Jacquemin, and Ling Shao, Senior

More information

A Feature Point Matching Based Approach for Video Objects Segmentation

A Feature Point Matching Based Approach for Video Objects Segmentation A Feature Point Matching Based Approach for Video Objects Segmentation Yan Zhang, Zhong Zhou, Wei Wu State Key Laboratory of Virtual Reality Technology and Systems, Beijing, P.R. China School of Computer

More information

CORRECTING CAMERA SHAKE BY INCREMENTAL SPARSE APPROXIMATION. Paul Shearer, Anna C. Gilbert, Alfred O. Hero III. University of Michigan, Ann Arbor

CORRECTING CAMERA SHAKE BY INCREMENTAL SPARSE APPROXIMATION. Paul Shearer, Anna C. Gilbert, Alfred O. Hero III. University of Michigan, Ann Arbor CORRECTING CAMERA SHAKE BY INCREMENTAL SPARSE APPROXIMATION Paul Shearer, Anna C. Gilbert, Alfred O. Hero III University of Michigan, Ann Arbor ABSTRACT The problem of deblurring an image when the blur

More information

Depth-Aware Motion Deblurring

Depth-Aware Motion Deblurring Depth-Aware Motion Deblurring Li Xu Jiaya Jia Department of Computer Science and Engineering The Chinese University of Hong Kong {xuli, leojia}@cse.cuhk.edu.hk Abstract Motion deblurring from images that

More information

Robust Model-Free Tracking of Non-Rigid Shape. Abstract

Robust Model-Free Tracking of Non-Rigid Shape. Abstract Robust Model-Free Tracking of Non-Rigid Shape Lorenzo Torresani Stanford University ltorresa@cs.stanford.edu Christoph Bregler New York University chris.bregler@nyu.edu New York University CS TR2003-840

More information

Blind Deconvolution of Camera Motioned Picture using Depth Map

Blind Deconvolution of Camera Motioned Picture using Depth Map Blind Deconvolution of Camera Motioned Picture using Depth Map B.Kalaiyarasi 1, S.Kalpana 2 II-M.E(CS) 1, AP / ECE 2, Dhanalakshmi Srinivasan Engineering College, Perambalur. Dhanalakshmi Srinivasan Engineering

More information

UNDERSTANDING IMAGE PRIORS IN BLIND DECONVOLUTION

UNDERSTANDING IMAGE PRIORS IN BLIND DECONVOLUTION UNDERSTANDING IMAGE PRIORS IN BLIND DECONVOLUTION Filip Šroubek, Václav Šmídl, Jan Kotera UTIA, Academy of Sciences of the Czech Republic, Prague, Czech Republic Charles University in Prague, Faculty of

More information

Part-based and local feature models for generic object recognition

Part-based and local feature models for generic object recognition Part-based and local feature models for generic object recognition May 28 th, 2015 Yong Jae Lee UC Davis Announcements PS2 grades up on SmartSite PS2 stats: Mean: 80.15 Standard Dev: 22.77 Vote on piazza

More information

Deblurring Natural Image Using Super-Gaussian Fields

Deblurring Natural Image Using Super-Gaussian Fields Deblurring Natural Image Using Super-Gaussian Fields Yuhang Liu 1 (https://orcid.org/-2-8195-9349), Wenyong Dong 1, Dong Gong 2, Lei Zhang 2, and Qinfeng Shi 2 1 Computer School, Wuhan University, Hubei,

More information

Graph-Based Blind Image Deblurring From a Single Photograph

Graph-Based Blind Image Deblurring From a Single Photograph Graph-Based Blind Image Deblurring From a Single Photograph Yuanchao Bai, Student Member, IEEE, Gene Cheung, Senior Member, IEEE, Xianming Liu, Member, IEEE, Wen Gao, Fellow, IEEE arxiv:82.7929v [cs.cv]

More information

Understanding and evaluating blind deconvolution algorithms

Understanding and evaluating blind deconvolution algorithms Understanding and evaluating blind deconvolution algorithms Anat Levin 1,2, Yair Weiss 1,3, Fredo Durand 1, William T. Freeman 1,4 1 MIT CSAIL, 2 Weizmann Institute of Science, 3 Hebrew University, 4 Adobe

More information

COMPRESSED FACE HALLUCINATION. Electrical Engineering and Computer Science University of California, Merced, CA 95344, USA

COMPRESSED FACE HALLUCINATION. Electrical Engineering and Computer Science University of California, Merced, CA 95344, USA COMPRESSED FACE HALLUCNATON Sifei Liu Ming-Hsuan Yang Electrical Engineering and Computer Science University of California, Merced, CA 95344, USA ABSTRACT n this paper, we propose an algorithm to hallucinate

More information

Registration Based Non-uniform Motion Deblurring

Registration Based Non-uniform Motion Deblurring Pacific Graphics 2012 C. Bregler, P. Sander, and M. Wimmer (Guest Editors) Volume 31 (2012), Number 7 Registration Based Non-uniform Motion Deblurring Sunghyun Cho 1 Hojin Cho 1 Yu-Wing Tai 2 Seungyong

More information

DUAL DEBLURRING LEVERAGED BY IMAGE MATCHING

DUAL DEBLURRING LEVERAGED BY IMAGE MATCHING DUAL DEBLURRING LEVERAGED BY IMAGE MATCHING Fang Wang 1,2, Tianxing Li 3, Yi Li 2 1 Nanjing University of Science and Technology, Nanjing, 210094 2 National ICT Australia, Canberra, 2601 3 Dartmouth College,

More information

Bindel, Spring 2015 Numerical Analysis (CS 4220) Figure 1: A blurred mystery photo taken at the Ithaca SPCA. Proj 2: Where Are My Glasses?

Bindel, Spring 2015 Numerical Analysis (CS 4220) Figure 1: A blurred mystery photo taken at the Ithaca SPCA. Proj 2: Where Are My Glasses? Figure 1: A blurred mystery photo taken at the Ithaca SPCA. Proj 2: Where Are My Glasses? 1 Introduction The image in Figure 1 is a blurred version of a picture that I took at the local SPCA. Your mission

More information

A Novel Multi-Frame Color Images Super-Resolution Framework based on Deep Convolutional Neural Network. Zhe Li, Shu Li, Jianmin Wang and Hongyang Wang

A Novel Multi-Frame Color Images Super-Resolution Framework based on Deep Convolutional Neural Network. Zhe Li, Shu Li, Jianmin Wang and Hongyang Wang 5th International Conference on Measurement, Instrumentation and Automation (ICMIA 2016) A Novel Multi-Frame Color Images Super-Resolution Framewor based on Deep Convolutional Neural Networ Zhe Li, Shu

More information

Specular Reflection Separation using Dark Channel Prior

Specular Reflection Separation using Dark Channel Prior 2013 IEEE Conference on Computer Vision and Pattern Recognition Specular Reflection Separation using Dark Channel Prior Hyeongwoo Kim KAIST hyeongwoo.kim@kaist.ac.kr Hailin Jin Adobe Research hljin@adobe.com

More information

ABSTRACT BLUR AND ILLUMINATION- INVARIANT FACE RECOGNITION VIA SET-THEORETIC CHARACTERIZATION

ABSTRACT BLUR AND ILLUMINATION- INVARIANT FACE RECOGNITION VIA SET-THEORETIC CHARACTERIZATION ABSTRACT Title of thesis: BLUR AND ILLUMINATION- INVARIANT FACE RECOGNITION VIA SET-THEORETIC CHARACTERIZATION Priyanka Vageeswaran, Master of Science, 2013 Thesis directed by: Professor Rama Chellappa

More information

Building a Panorama. Matching features. Matching with Features. How do we build a panorama? Computational Photography, 6.882

Building a Panorama. Matching features. Matching with Features. How do we build a panorama? Computational Photography, 6.882 Matching features Building a Panorama Computational Photography, 6.88 Prof. Bill Freeman April 11, 006 Image and shape descriptors: Harris corner detectors and SIFT features. Suggested readings: Mikolajczyk

More information

TAKING good pictures in low-light conditions is perhaps

TAKING good pictures in low-light conditions is perhaps IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL. 40, NO. 10, OCTOBER 2018 2329 Deblurring Low-Light Images with Light Streaks Zhe Hu, Sunghyun Cho, Jue Wang, Senior Member, IEEE, and

More information

Markov Random Fields and Gibbs Sampling for Image Denoising

Markov Random Fields and Gibbs Sampling for Image Denoising Markov Random Fields and Gibbs Sampling for Image Denoising Chang Yue Electrical Engineering Stanford University changyue@stanfoed.edu Abstract This project applies Gibbs Sampling based on different Markov

More information

Image restoration. Restoration: Enhancement:

Image restoration. Restoration: Enhancement: Image restoration Most images obtained by optical, electronic, or electro-optic means is likely to be degraded. The degradation can be due to camera misfocus, relative motion between camera and object,

More information

Photometric Stereo with Auto-Radiometric Calibration

Photometric Stereo with Auto-Radiometric Calibration Photometric Stereo with Auto-Radiometric Calibration Wiennat Mongkulmann Takahiro Okabe Yoichi Sato Institute of Industrial Science, The University of Tokyo {wiennat,takahiro,ysato} @iis.u-tokyo.ac.jp

More information

A MAP-Estimation Framework for Blind Deblurring Using High-Level Edge Priors

A MAP-Estimation Framework for Blind Deblurring Using High-Level Edge Priors A MAP-Estimation Framework for Blind Deblurring Using High-Level Edge Priors Yipin Zhou 1 and Nikos Komodakis 2 1 Brown University, USA yipin zhou@brown.edu 2 Universite Paris-Est, Ecole des Ponts ParisTech,

More information

Motion Deblurring With Graph Laplacian Regularization

Motion Deblurring With Graph Laplacian Regularization Motion Deblurring With Graph Laplacian Regularization Amin Kheradmand and Peyman Milanfar Department of Electrical Engineering University of California, Santa Cruz ABSTRACT In this paper, we develop a

More information

Learning to Super-Resolve Blurry Face and Text Images

Learning to Super-Resolve Blurry Face and Text Images Learning to Super-Resolve Blurry Face and Text Images Xiangyu Xu,2,3 Deqing Sun 3,4 Jinshan Pan 5 Yujin Zhang Hanspeter Pfister 3 Ming-Hsuan Yang 2 Tsinghua University 2 University of California, Merced

More information

Augmented Reality VU. Computer Vision 3D Registration (2) Prof. Vincent Lepetit

Augmented Reality VU. Computer Vision 3D Registration (2) Prof. Vincent Lepetit Augmented Reality VU Computer Vision 3D Registration (2) Prof. Vincent Lepetit Feature Point-Based 3D Tracking Feature Points for 3D Tracking Much less ambiguous than edges; Point-to-point reprojection

More information

Handling Noise in Single Image Deblurring using Directional Filters

Handling Noise in Single Image Deblurring using Directional Filters 2013 IEEE Conference on Computer Vision and Pattern Recognition Handling Noise in Single Image Deblurring using Directional Filters Lin Zhong 1 Sunghyun Cho 2 Dimitris Metaxas 1 Sylvain Paris 2 Jue Wang

More information

Comparative Analysis of Edge Based Single Image Superresolution

Comparative Analysis of Edge Based Single Image Superresolution Comparative Analysis of Edge Based Single Image Superresolution Sonali Shejwal 1, Prof. A. M. Deshpande 2 1,2 Department of E&Tc, TSSM s BSCOER, Narhe, University of Pune, India. ABSTRACT: Super-resolution

More information

Richardson-Lucy Deblurring for Scenes under Projective Motion Path

Richardson-Lucy Deblurring for Scenes under Projective Motion Path 1 Richardson-Lucy Deblurring for Scenes under Projective Motion Path Yu-Wing Tai Ping Tan Long Gao Michael S. Brown Abstract This paper addresses the problem of modeling and correcting image blur caused

More information

PSF ACCURACY MEASURE FOR EVALUATION OF BLUR ESTIMATION ALGORITHMS

PSF ACCURACY MEASURE FOR EVALUATION OF BLUR ESTIMATION ALGORITHMS PSF ACCURACY MEASURE FOR EVALUATION OF BLUR ESTIMATION ALGORITHMS Jan Kotera 1,, Barbara Zitová 1, Filip Šroubek 1 1 UTIA, Czech Academy of Sciences, Prague, Czech Republic Charles University in Prague,

More information

RESTORING ARTIFACT-FREE MICROSCOPY IMAGE SEQUENCES. Robotics Institute Carnegie Mellon University 5000 Forbes Ave, Pittsburgh, PA 15213, USA

RESTORING ARTIFACT-FREE MICROSCOPY IMAGE SEQUENCES. Robotics Institute Carnegie Mellon University 5000 Forbes Ave, Pittsburgh, PA 15213, USA RESTORING ARTIFACT-FREE MICROSCOPY IMAGE SEQUENCES Zhaozheng Yin Takeo Kanade Robotics Institute Carnegie Mellon University 5000 Forbes Ave, Pittsburgh, PA 15213, USA ABSTRACT Phase contrast and differential

More information

Computer Vision 2. SS 18 Dr. Benjamin Guthier Professur für Bildverarbeitung. Computer Vision 2 Dr. Benjamin Guthier

Computer Vision 2. SS 18 Dr. Benjamin Guthier Professur für Bildverarbeitung. Computer Vision 2 Dr. Benjamin Guthier Computer Vision 2 SS 18 Dr. Benjamin Guthier Professur für Bildverarbeitung Computer Vision 2 Dr. Benjamin Guthier 1. IMAGE PROCESSING Computer Vision 2 Dr. Benjamin Guthier Content of this Chapter Non-linear

More information

TEMPORALLY CONSISTENT REGION-BASED VIDEO EXPOSURE CORRECTION

TEMPORALLY CONSISTENT REGION-BASED VIDEO EXPOSURE CORRECTION TEMPORALLY CONSISTENT REGION-BASED VIDEO EXPOSURE CORRECTION Xuan Dong 1, Lu Yuan 2, Weixin Li 3, Alan L. Yuille 3 Tsinghua University 1, Microsoft Research Asia 2, UC Los Angeles 3 dongx10@mails.tsinghua.edu.cn,

More information

INTRINSIC IMAGE DECOMPOSITION BY HIERARCHICAL L 0 SPARSITY

INTRINSIC IMAGE DECOMPOSITION BY HIERARCHICAL L 0 SPARSITY INTRINSIC IMAGE DECOMPOSITION BY HIERARCHICAL L 0 SPARSITY Xuecheng Nie 1,2, Wei Feng 1,3,, Liang Wan 2,3, Haipeng Dai 1, Chi-Man Pun 4 1 School of Computer Science and Technology, Tianjin University,

More information

3D Computer Vision. Dense 3D Reconstruction II. Prof. Didier Stricker. Christiano Gava

3D Computer Vision. Dense 3D Reconstruction II. Prof. Didier Stricker. Christiano Gava 3D Computer Vision Dense 3D Reconstruction II Prof. Didier Stricker Christiano Gava Kaiserlautern University http://ags.cs.uni-kl.de/ DFKI Deutsches Forschungszentrum für Künstliche Intelligenz http://av.dfki.de

More information

CNN for Low Level Image Processing. Huanjing Yue

CNN for Low Level Image Processing. Huanjing Yue CNN for Low Level Image Processing Huanjing Yue 2017.11 1 Deep Learning for Image Restoration General formulation: min Θ L( x, x) s. t. x = F(y; Θ) Loss function Parameters to be learned Key issues The

More information

arxiv: v1 [cs.cv] 25 Dec 2017

arxiv: v1 [cs.cv] 25 Dec 2017 Deep Blind Image Inpainting Yang Liu 1, Jinshan Pan 2, Zhixun Su 1 1 School of Mathematical Sciences, Dalian University of Technology 2 School of Computer Science and Engineering, Nanjing University of

More information

ROBUST INTERNAL EXEMPLAR-BASED IMAGE ENHANCEMENT. Yang Xian 1 and Yingli Tian 1,2

ROBUST INTERNAL EXEMPLAR-BASED IMAGE ENHANCEMENT. Yang Xian 1 and Yingli Tian 1,2 ROBUST INTERNAL EXEMPLAR-BASED IMAGE ENHANCEMENT Yang Xian 1 and Yingli Tian 1,2 1 The Graduate Center, 2 The City College, The City University of New York, New York, Email: yxian@gc.cuny.edu; ytian@ccny.cuny.edu

More information

Segmentation. Bottom up Segmentation Semantic Segmentation

Segmentation. Bottom up Segmentation Semantic Segmentation Segmentation Bottom up Segmentation Semantic Segmentation Semantic Labeling of Street Scenes Ground Truth Labels 11 classes, almost all occur simultaneously, large changes in viewpoint, scale sky, road,

More information

Redundancy Encoding for Fast Dynamic MR Imaging using Structured Sparsity

Redundancy Encoding for Fast Dynamic MR Imaging using Structured Sparsity Redundancy Encoding for Fast Dynamic MR Imaging using Structured Sparsity Vimal Singh and Ahmed H. Tewfik Electrical and Computer Engineering Dept., The University of Texas at Austin, USA Abstract. For

More information

EECS 556 Image Processing W 09. Image enhancement. Smoothing and noise removal Sharpening filters

EECS 556 Image Processing W 09. Image enhancement. Smoothing and noise removal Sharpening filters EECS 556 Image Processing W 09 Image enhancement Smoothing and noise removal Sharpening filters What is image processing? Image processing is the application of 2D signal processing methods to images Image

More information

Deep Learning with Tensorflow AlexNet

Deep Learning with Tensorflow   AlexNet Machine Learning and Computer Vision Group Deep Learning with Tensorflow http://cvml.ist.ac.at/courses/dlwt_w17/ AlexNet Krizhevsky, Alex, Ilya Sutskever, and Geoffrey E. Hinton, "Imagenet classification

More information