Super-Resolution. Many slides from Miki Elad Technion Yosi Rubner RTC and more

Size: px
Start display at page:

Download "Super-Resolution. Many slides from Miki Elad Technion Yosi Rubner RTC and more"

Transcription

1 Super-Resolution Many slides from Mii Elad Technion Yosi Rubner RTC and more 1

2 Example - Video 53 images, ratio 1:4 2

3 Example Surveillance 40 images ratio 1:4 3

4 Example Enhance Mosaics 4

5 5

6 Super-Resolution - Agenda The basic idea Image formation process Formulation and solution Special cases and related problems SR in time SR from Examples 6

7 Intuition For a given band-limited image, the Nyquist sampling theorem states that if a uniform sampling is fine enough ( D), perfect reconstruction is possible. D D 7

8 Intuition Due to our limited camera resolution, we sample using an insufficient 2D grid 2D 2D 8

9 Intuition However, if we tae a second picture, shifting the camera slightly to the right we obtain: 2D 2D 9

10 Intuition Similarly, by shifting down we get a third image: 2D 2D 10

11 Intuition And finally, by shifting down and to the right we get the fourth image: 2D 2D 11

12 Intuition It is trivial to see that interlacing the four images, we get that the desired resolution is obtained, and thus perfect reconstruction is guaranteed. 12

13 Rotation/Scale/Disp. What if the camera displacement is Arbitrary? What if the camera rotates? Gets closer to the object (zoom)? 13

14 Rotation/Scale/Disp. There is no sampling theorem covering this case 14

15 A Small Example 3:1 scale-up in each axis using 9 images, with pure global translation between them 15

16 Further Complications Complicated motion perspective, local motion, Blur sampling is not a point operation Spatially variant blur Temporally variant blur Noise Changes in the scene 16

17 Super-Resolution - Agenda The basic idea Image formation process Formulation and solution Special cases and related problems SR in time SR from Examples 17

18 Image Formation Scene HR Geometric transformation F Optical Blur H Sampling D Image LR Can we write these steps as linear operators? LR H F HR = D 18

19 Geometric Transformation F Scene Geometric transformation Any appropriate motion model Every frame has different transformation Usually found by a separate registration algorithm 19

20 Geometric Transformation Can be modeled as a linear operation F X F = X F X F X 20

21 Optical Blur H Geometric transformation Optical Blur Due to the lens PSF and pixel integration Usually H = H 21

22 H PSF * PIXEL = H 22

23 Optical Blur Can be modeled as a linear operation HX H = X HX H X 23

24 Sampling D Optical Blur Sampling Pixel operation consists of area integration followed by decimation D is the decimation only Usually D = D 24

25 Decimation Can be modeled as a linear operation DX D X DX o o D 1 0 X = 25

26 Image Formation Scene HR Geometric transformation F Optical Blur H Sampling D Image LR LR= D H F HR 26

27 Image Formation + Scene HR Image LR Noise N LR D H F HR+ = N 27

28 Super-Resolution - Agenda The basic idea Image formation process Formulation and solution Special cases and related problems SR in time SR from Examples 28

29 Super-Resolution - Model Geometric warp Blur Decimation High- Resolution Image X F =I 1 H 1 D 1 V 1 Y 1 Low- Resolution Exposures Additive Noise F N H N D N Y N Y V N { 2 0, } = D H F X + V, V ~ N σ n N = 1 29

30 Simplified Model Geometric warp Blur Decimation High- Resolution Image X F =I 1 H D V 1 Y 1 Low- Resolution Exposures Additive Noise F N H D Y N Y V N { 2 0, } = DHF X + V, V ~ N σ n N = 1 30

31 The Super-Resolution Problem Y = DHF X + V { 0, 2 } σ, V ~ N n Given Y The measured images (noisy, blurry, down-sampled..) H The blur can be extracted from the camera characteristics D The decimation is dictated by the required resolution ratio F The warp can be estimated using motion estimation σ n The noise can be extracted from the camera / image Recover X HR image 31

32 The Model as One Equation Y Y1 D1H 1F1 V1 Y V 2 D2H2F2 X + 2 = = = GX M M M Y N DNHNFN V N + V Y G r = resolution factor = 4 MXM = size of the frames = 1000X1000 N = number of frames = 10 of of X, V size size of 2 [ NM 1] [ NM r M ] 2 2 [ r M 1] size =[10M 1] =[10M 16M] =[16M 1] Linear algebra notation is intended only to develop algorithm 32

33 SR - Solutions Maximum Lielihood (ML): X = X argmin X X N = 1 N =1 DHF X Y 2 Often ill posed problem! Maximum Aposteriori Probability (MAP) = argmin DHF X Y 2 { } +λa X Smoothness constraint regularization33

34 ML Reconstruction (LS) ( ) = = N ML Y X X DHF ε Minimize: ( ) ( ) 0 ˆ = = = N T T T ML Y X X X DHF H D F ε Thus, require: N T T T N T T T Y X = = = 1 1 ˆ D H F DHF D H F A B B A = Xˆ 34

35 LS - Iterative Solution Steepest descent Xˆ N T T T n+ = Xˆ β 1 n F H D n = 1 ( DHF Xˆ Y ) Bac projection Simulated error All the above operations can be interpreted as operations performed on images. There is no actual need to use the Matrix-Vector notations as shown here. 35

36 LS - Iterative Solution Steepest descent ( ) T T T Xˆ n+ = Xˆ 1 n β F H D DHF Xˆ n Y N = 1 For =1..N Xˆ n Y geometry wrap convolve with H down sample - up sample convolve with H T inverse geometry wrap F H D T D T H T F -β Xˆ n+1 36

37 Example HR image LR + noise X4 Least squares Simulated example from Farisu at al. IEEE trans. On Image Processing, 04 37

38 Robust Reconstruction Cases of measurement outlier: Some of the images are irrelevant Error in motion estimation Error in the blur function General model mismatch 38

39 Robust Reconstruction Minimize: ε 2 N ( X ) = = 1 DHF X Y 1 Xˆ N T T T n+ = Xˆ β 1 n F H D sign n = 1 ( DHF Xˆ Y ) 39

40 Robust Reconstruction Steepest descent For =1..N Xˆ n Xˆ N T T T n+ = Xˆ 1 n β F H D sign n = 1 Y ( DHF Xˆ Y ) geometry wrap convolve with H down sample - sign up sample convolve with H T inverse geometry wrap F H D T D T H T F -β ˆ 40 X n+1

41 Example - Outliers Least squares HR image LR + noise X4 Simulated example from Farisu at al. IEEE trans. On Image Processing, 04 Robust Reconstruction 41

42 Example Registration Error L 2 norm based L 1 norm based 20 images, ratio 1:4 42

43 MAP Reconstruction 2 MAP Regularization term: N = ( X ) DHF X Y λa{ X} ε + =1 2 Tihonov cost function A T { X } = ΓX 2 Total variation A TV { X } = X 1 Bilateral filter A B P P { X } = l= P m= P α l + m X S l x S m y X 1 43

44 Robust Estimation + Regularization ( ) = = + = + = P P l P P m m y l x m l N X S S X Y X X α λ ε DHF Minimize: ( ) [ ] ( ) + = = = + = + P P l P P m n m y l x n m y l x m l N n T T T n n X S S X S S I Y X X X ˆ ˆ sign ˆ sign ˆ ˆ 1 1 α λ β DHF H D F 44

45 Example 8 frames Resolution factor of 4 From Farisu at al. IEEE trans. On Image Processing, 04 45

46 Example Images from Vigilant Ltd. 46

47 Handling Color in SR 2 MAP N = ( X ) DHF X Y λa{ X} ε + =1 Handling color: the classic approach is to convert the measurements to YCbCr, apply the SR on the Y and use trivial interpolation on the Cb and Cr. Better treatment can be obtained if the statistical dependencies between the color layers are taen into account (i.e. forming a prior for color images). In case of mosaiced measurements, demosaicing followed by SR is sub-optimal. An algorithm that directly fuse the mosaic information to the SR is better. 2 47

48 SR for Full Color 20 images, ratio 1:4 48

49 SR+Demosaicing 20 images, ratio 1:4 Mosaiced input Mosaicing and then SR Combined treatment 49

50 Super-Resolution - Agenda The basic idea Image formation process Formulation and solution Special cases and related problems SR in time SR from Examples 50

51 Special Case Translational Motion In this case H and F commute (bloc circulant): T T HF = F H H F = F T H T Y = = = DHF X + V DF H X + V DF Z + V Z = H X SR is decomposed into 2 steps 1. Find blur HR image from LR images non-iterative 2. Deconvolve the result using H iterative 51

52 Intuition Y = DF Z + V Z = H X X Z=PSF*X Using the samples can, at most, reconstruct Z To recover X, need to deconvolve Z 52

53 Step I Find Blurred HR Minimize: ε 2 ML N ( Z) = = 1 DF Z Y 2 L 2 For all frames, copy registered pixels to HR grid and average [Elad & Hel-Or, 01] L 1 For all frames, copy registered pixels to HR grid and use median [Farisu, 04] 53

54 Solution for L 2 ( ) = = N ML Y Z Z DF ε Minimize: = = = = N T T N T T Y P 1 1 D F DF D F R Z = P ˆ R ( ) 0 2 = Z Z ε ML Thus, require: Sum of HR grid Diagonal, number Of occurrences per HR grid 54

55 Step II - Deblur ( ) { } A X Z X X λ ε + = 2 2 H Minimize: ( ) { } + = + n n n T n n X A X Z X X X ˆ ˆ ˆ ˆ ˆ 1 λ β H H 55

56 Example 64X64 LR 256X256 Before deblur 256X256 After deblur From Pham at al. Proc. Of SPIE-IS&T, 05. Simulated. 56

57 Super-Resolution - Agenda The basic idea Image formation process Formulation and solution Special cases and related problems SR in time SR from Examples 57

58 Classical Image Super-Resolution Low-resolution images: Scene: High-resolution image: 58

59 Space-Time Super-Resolution Low-resolution images video sequences: time time time High space-time resolution sequence: time time Super-resolution in space and in time. 59

60 What is Super-Resolution in Time? Observing events faster than frame-rate. Handles: (1) Motion aliasing (2) Motion blur Application areas: - sports scenes - scientific imaging - etc... 60

61 (1) Motion Aliasing The Wagon wheel effect: Slow-motion: time time time Continuous signal Sub-sampled in time Slow motion 61

62 (2) Motion Blur 62

63 (2) Motion Blur Camera 1: long exposuretime Camera 2: short exposuretime Motion-blur A Spatial artifact caused by Temporal blurring. Operation of camera: exposure time time time 1/frame-rate 1/frame-rate 63

64 Space-Time Super-Resolution S h (x h,y h,t h ) y t T x x y Blur ernel: PSF l S 1 l S n Exposure time t 64

65 Example: Motion-Aliasing Input 1 Input 2 Input 3 Input 4 25 [frames/sec] 65

66 Example: Motion-Aliasing Input sequence in slow-motion (x3): Super-resolution resolution in time (x3): 75 [frames/sec] 75 [frames/sec] 66

67 Output sequence: Output trajectory: Deblurring: Input: (x15 frame-rate) Without estimating motion of the ball! Output: 3 out of 18 low-resolution input sequences (frame overlays; trajectories): 67

68 Example: Motion-Blur (real) Frames 4 input at sequences: collision: Video 1 Video 2 Output frame at collision: Video 3 Video 4 68

69 Super-Resolution - Agenda The basic idea Image formation process Formulation and solution Special cases and related problems SR in time SR from Examples 69

70 Example Based Super Resolution Image is complex for a generative model to model Non-parametric methods Texture synthesis [Efros99],[Feng04] Motion synthesis [Li02] Resolution synthesis

71 Example Based Super Resolution Generate a high-resolution image from a single low-resolution image, with the help of a set of training images. Slides from Gu, Yu, Tian, Belorylov 2006

72 Example Based Super Resolution Output HR Input LR Training Set (Low-High resolution image pairs) Training Set

73 Extensions Super-resolution Through Neighbor Embedding (Manifold learning) 1. For each patch x in image LR image: (a) Find K nearest neighbors in the training set t 1 t. (b) Compute the reconstruction weights w 1 w of the neighbors that minimize the error of reconstructing x. min w1... w (c) Compute HR y as a weighted linear combination of the corresponding high-resolution patches T i using the weights w 1 w. y x = i i w t i w i T i H. Chang, D.Y. Yeung, Y. Xiong, Super-resolution through neighbor embedding, 2004 i 2

74 Super-resolution Through Neighbor Embedding (Manifold learning,lle) Training Set 3x3 * * * * * w1 + w2 + w3 + w4 + w5 * * * * * w1 + w2 + w3 + w4 + w5 9x9

75 Super-resolution Through Neighbor Embedding (Manifold learning,lle) Input LR image True HR image Neighborhood Embedding Interpolation

76 Super-resolution Using High Low Frequency matching pairs Basic idea Divide the image into frequencies (L,M,H) Construct database to store the relations of midfrequency and corresponding high frequency Interpolation for initial magnification Add high frequency details by searching in the training database Freeman, Jones, Pasztor Example Based Super Resolution, 2002

77 Training phase Blur downsample interpolation High-frequency filter Mid-frequency 1/9 1/9 1/9 1/9 8/9 1/9 1/9 1/9 1/9

78 Data Set Low resolution patches High resolution patches

79 Input LR Retrieval phase interpolation filter 1/9 1/9 1/9 1/9 8/9 1/9 1/9 1/9 1/9 Output HR Training Set + Mid-frequency High-frequency

80 Super-resolution Using High Low Frequency matching pairs Input LR image True HR image High-Low Frequency Interpolation

81 Super-resolution Using High Low Frequency matching pairs Interpolation Output HR image

82 Super-resolution Comparison Weighted Manifold restores high res patch by computing weighted combination of high res patches in training set. High-Low Freq Example Based Algorithm finds the best high res patch in Training Set whose low res is most similar to the patch. Weighted Manifold Low-High Freq

83 Overlapping of Patches For each patch embed the computed high res patch. Use overlapping patches. 1. For each pixel in overlap, compute average over all high res pixels. B1 B2 Overlap Average 2. Use Optimal Cut to combine overlapping patches. B1 B2 Minimal error boundary cut

84 Overlapping of Patches 3. Grow image and apply neighboring high res constraints. a. Choose best matches for patch and select that which best fits the neighboring constraints. b. Select best matches and use MRF to select patches so that neighboring patches are smooth.

85 SR by Examples Training set limitation It might seem that SR of an image of one feature (eg, a cat) requires a training set that contains these features (images of other cats). However, this isn t the case.

86 SR by Examples Training set limitation Although the training set doesn t have to be very similar to the image to be enlarged, it should be in the same image class such as text or color image.

87 SR from a Single Image SR based on multiple LR images SR based on Database of Images. Can SR be obtained from a single image??

88 SR from a Single Image Use repetitions in single image.

89 SR from a Single Image Patches in image are found at different locations and scale. Use different scale to predict what high res of patch should loo lie. Glasner, Bigon & Irani Super resolution from a Single Image, 2010

90 SR from a Single Image HR from many LR images LR patches induce constraints on HR image. Multi patch LR in single image induces same ind of constraints. Multi scale patch in single image form an Example.

91 SR from a Single Image Multi Resolution approach combines 2 approaches: 1) Multi LR Images to High res 2) SR based on Examples

92 SR from a Single Image Glasner, Bigon & Irani Super resolution from a Single Image, 2010

93 SR from a Single Image Bicubic x3 SR from Single Image x3 Glasner, Bigon & Irani Super resolution from a Single Image, 2010

94

Introduction to Image Super-resolution. Presenter: Kevin Su

Introduction to Image Super-resolution. Presenter: Kevin Su Introduction to Image Super-resolution Presenter: Kevin Su References 1. S.C. Park, M.K. Park, and M.G. KANG, Super-Resolution Image Reconstruction: A Technical Overview, IEEE Signal Processing Magazine,

More information

Super Resolution Using Graph-cut

Super Resolution Using Graph-cut Super Resolution Using Graph-cut Uma Mudenagudi, Ram Singla, Prem Kalra, and Subhashis Banerjee Department of Computer Science and Engineering Indian Institute of Technology Delhi Hauz Khas, New Delhi,

More information

Enhancing DubaiSat-1 Satellite Imagery Using a Single Image Super-Resolution

Enhancing DubaiSat-1 Satellite Imagery Using a Single Image Super-Resolution Enhancing DubaiSat-1 Satellite Imagery Using a Single Image Super-Resolution Saeed AL-Mansoori 1 and Alavi Kunhu 2 1 Associate Image Processing Engineer, SIPAD Image Enhancement Section Emirates Institution

More information

EFFICIENT PERCEPTUAL, SELECTIVE,

EFFICIENT PERCEPTUAL, SELECTIVE, EFFICIENT PERCEPTUAL, SELECTIVE, AND ATTENTIVE SUPER-RESOLUTION RESOLUTION Image, Video & Usability (IVU) Lab School of Electrical, Computer, & Energy Engineering Arizona State University karam@asu.edu

More information

Performance study on point target detection using super-resolution reconstruction

Performance study on point target detection using super-resolution reconstruction Performance study on point target detection using super-resolution reconstruction Judith Dijk a,adamw.m.vaneekeren ab, Klamer Schutte a Dirk-Jan J. de Lange a, Lucas J. van Vliet b a Electro Optics Group

More information

Resolution Magnification Technique for Satellite Images Using DT- CWT and NLM

Resolution Magnification Technique for Satellite Images Using DT- CWT and NLM AUSTRALIAN JOURNAL OF BASIC AND APPLIED SCIENCES ISSN:1991-8178 EISSN: 2309-8414 Journal home page: www.ajbasweb.com Resolution Magnification Technique for Satellite Images Using DT- CWT and NLM 1 Saranya

More information

Dense Image-based Motion Estimation Algorithms & Optical Flow

Dense Image-based Motion Estimation Algorithms & Optical Flow Dense mage-based Motion Estimation Algorithms & Optical Flow Video A video is a sequence of frames captured at different times The video data is a function of v time (t) v space (x,y) ntroduction to motion

More information

IMAGE RECONSTRUCTION WITH SUPER RESOLUTION

IMAGE RECONSTRUCTION WITH SUPER RESOLUTION INTERNATIONAL JOURNAL OF RESEARCH IN COMPUTER APPLICATIONS AND ROBOTICS ISSN 2320-7345 IMAGE RECONSTRUCTION WITH SUPER RESOLUTION B.Vijitha 1, K.SrilathaReddy 2 1 Asst. Professor, Department of Computer

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

Super-Resolution (SR) image re-construction is the process of combining the information from multiple

Super-Resolution (SR) image re-construction is the process of combining the information from multiple Super-Resolution Super-Resolution (SR) image re-construction is the process of combining the information from multiple Low-Resolution (LR) aliased and noisy frames of the same scene to estimate a High-Resolution

More information

Super-Resolution Image with Estimated High Frequency Compensated Algorithm

Super-Resolution Image with Estimated High Frequency Compensated Algorithm Super-Resolution with Estimated High Frequency Compensated Algorithm Jong-Tzy Wang, 2 Kai-Wen Liang, 2 Shu-Fan Chang, and 2 Pao-Chi Chang 1 Department of Electronic Engineering, Jinwen University of Science

More information

Image Restoration. Diffusion Denoising Deconvolution Super-resolution Tomographic Reconstruction

Image Restoration. Diffusion Denoising Deconvolution Super-resolution Tomographic Reconstruction Image Restoration Image Restoration Diffusion Denoising Deconvolution Super-resolution Tomographic Reconstruction Diffusion Term Consider only the regularization term E-L equation: (Laplace equation) Steepest

More information

Robust Video Super-Resolution with Registration Efficiency Adaptation

Robust Video Super-Resolution with Registration Efficiency Adaptation Robust Video Super-Resolution with Registration Efficiency Adaptation Xinfeng Zhang a, Ruiqin Xiong b, Siwei Ma b, Li Zhang b, Wen Gao b a Institute of Computing Technology, Chinese Academy of Sciences,

More information

Edge-Preserving MRI Super Resolution Using a High Frequency Regularization Technique

Edge-Preserving MRI Super Resolution Using a High Frequency Regularization Technique Edge-Preserving MRI Super Resolution Using a High Frequency Regularization Technique Kaveh Ahmadi Department of EECS University of Toledo, Toledo, Ohio, USA 43606 Email: Kaveh.ahmadi@utoledo.edu Ezzatollah

More information

Super-Resolution on Moving Objects and Background

Super-Resolution on Moving Objects and Background Super-Resolution on Moving Objects and Background A. van Eekeren K. Schutte J. Dijk D.J.J. de Lange L.J. van Vliet TNO Defence, Security and Safety, P.O. Box 96864, 2509 JG, The Hague, The Netherlands

More information

Image Processing Via Pixel Permutations

Image Processing Via Pixel Permutations Image Processing Via Pixel Permutations Michael Elad The Computer Science Department The Technion Israel Institute of technology Haifa 32000, Israel Joint work with Idan Ram Israel Cohen The Electrical

More information

Patch Based Blind Image Super Resolution

Patch Based Blind Image Super Resolution Patch Based Blind Image Super Resolution Qiang Wang, Xiaoou Tang, Harry Shum Microsoft Research Asia, Beijing 100080, P.R. China {qiangwa,xitang,hshum@microsoft.com} Abstract In this paper, a novel method

More information

Super-resolution on Text Image Sequences

Super-resolution on Text Image Sequences November 4, 2004 Outline Outline Geometric Distortion Optical/Motion Blurring Down-Sampling Total Variation Basic Idea Outline Geometric Distortion Optical/Motion Blurring Down-Sampling No optical/image

More information

GRID WARPING IN TOTAL VARIATION IMAGE ENHANCEMENT METHODS. Andrey Nasonov, and Andrey Krylov

GRID WARPING IN TOTAL VARIATION IMAGE ENHANCEMENT METHODS. Andrey Nasonov, and Andrey Krylov GRID WARPING IN TOTAL VARIATION IMAGE ENHANCEMENT METHODS Andrey Nasonov, and Andrey Krylov Lomonosov Moscow State University, Moscow, Department of Computational Mathematics and Cybernetics, e-mail: nasonov@cs.msu.ru,

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

ME/CS 132: Introduction to Vision-based Robot Navigation! Low-level Image Processing" Larry Matthies"

ME/CS 132: Introduction to Vision-based Robot Navigation! Low-level Image Processing Larry Matthies ME/CS 132: Introduction to Vision-based Robot Navigation! Low-level Image Processing" Larry Matthies" lhm@jpl.nasa.gov, 818-354-3722" Announcements" First homework grading is done! Second homework is due

More information

Novel Iterative Back Projection Approach

Novel Iterative Back Projection Approach IOSR Journal of Computer Engineering (IOSR-JCE) e-issn: 2278-0661, p- ISSN: 2278-8727Volume 11, Issue 1 (May. - Jun. 2013), PP 65-69 Novel Iterative Back Projection Approach Patel Shreyas A. Master in

More information

Learning based face hallucination techniques: A survey

Learning based face hallucination techniques: A survey Vol. 3 (2014-15) pp. 37-45. : A survey Premitha Premnath K Department of Computer Science & Engineering Vidya Academy of Science & Technology Thrissur - 680501, Kerala, India (email: premithakpnath@gmail.com)

More information

CSE 190A Super-Resolution

CSE 190A Super-Resolution CSE 190A SuperResolution Thomas Cassey EAP Student Department of Computer Science University of California San Diego tcassey@ucsd.edu Abstract This paper details the implementation of a multiframe superresolution

More information

Image Stitching. Slides from Rick Szeliski, Steve Seitz, Derek Hoiem, Ira Kemelmacher, Ali Farhadi

Image Stitching. Slides from Rick Szeliski, Steve Seitz, Derek Hoiem, Ira Kemelmacher, Ali Farhadi Image Stitching Slides from Rick Szeliski, Steve Seitz, Derek Hoiem, Ira Kemelmacher, Ali Farhadi Combine two or more overlapping images to make one larger image Add example Slide credit: Vaibhav Vaish

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

2D rendering takes a photo of the 2D scene with a virtual camera that selects an axis aligned rectangle from the scene. The photograph is placed into

2D rendering takes a photo of the 2D scene with a virtual camera that selects an axis aligned rectangle from the scene. The photograph is placed into 2D rendering takes a photo of the 2D scene with a virtual camera that selects an axis aligned rectangle from the scene. The photograph is placed into the viewport of the current application window. A pixel

More information

Optical Flow Estimation

Optical Flow Estimation Optical Flow Estimation Goal: Introduction to image motion and 2D optical flow estimation. Motivation: Motion is a rich source of information about the world: segmentation surface structure from parallax

More information

A Fast Super-Resolution Reconstruction Algorithm for Pure Translational Motion and Common Space-Invariant Blur

A Fast Super-Resolution Reconstruction Algorithm for Pure Translational Motion and Common Space-Invariant Blur IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL. 10, NO. 8, AUGUST 2001 1187 A Fast Super-Resolution Reconstruction Algorithm for Pure Translational Motion and Common Space-Invariant Blur Michael Elad, Member,

More information

A Novel Image Super-resolution Reconstruction Algorithm based on Modified Sparse Representation

A Novel Image Super-resolution Reconstruction Algorithm based on Modified Sparse Representation , pp.162-167 http://dx.doi.org/10.14257/astl.2016.138.33 A Novel Image Super-resolution Reconstruction Algorithm based on Modified Sparse Representation Liqiang Hu, Chaofeng He Shijiazhuang Tiedao University,

More information

Motion Tracking and Event Understanding in Video Sequences

Motion Tracking and Event Understanding in Video Sequences Motion Tracking and Event Understanding in Video Sequences Isaac Cohen Elaine Kang, Jinman Kang Institute for Robotics and Intelligent Systems University of Southern California Los Angeles, CA Objectives!

More information

ELEC Dr Reji Mathew Electrical Engineering UNSW

ELEC Dr Reji Mathew Electrical Engineering UNSW ELEC 4622 Dr Reji Mathew Electrical Engineering UNSW Review of Motion Modelling and Estimation Introduction to Motion Modelling & Estimation Forward Motion Backward Motion Block Motion Estimation Motion

More information

Single-Image Super-Resolution Using Multihypothesis Prediction

Single-Image Super-Resolution Using Multihypothesis Prediction Single-Image Super-Resolution Using Multihypothesis Prediction Chen Chen and James E. Fowler Department of Electrical and Computer Engineering, Geosystems Research Institute (GRI) Mississippi State University,

More information

FAST SINGLE-IMAGE SUPER-RESOLUTION WITH FILTER SELECTION. Image Processing Lab Technicolor R&I Hannover

FAST SINGLE-IMAGE SUPER-RESOLUTION WITH FILTER SELECTION. Image Processing Lab Technicolor R&I Hannover FAST SINGLE-IMAGE SUPER-RESOLUTION WITH FILTER SELECTION Jordi Salvador Eduardo Pérez-Pellitero Axel Kochale Image Processing Lab Technicolor R&I Hannover ABSTRACT This paper presents a new method for

More information

Video Alignment. Literature Survey. Spring 2005 Prof. Brian Evans Multidimensional Digital Signal Processing Project The University of Texas at Austin

Video Alignment. Literature Survey. Spring 2005 Prof. Brian Evans Multidimensional Digital Signal Processing Project The University of Texas at Austin Literature Survey Spring 2005 Prof. Brian Evans Multidimensional Digital Signal Processing Project The University of Texas at Austin Omer Shakil Abstract This literature survey compares various methods

More information

Multi-stable Perception. Necker Cube

Multi-stable Perception. Necker Cube Multi-stable Perception Necker Cube Spinning dancer illusion, Nobuyuki Kayahara Multiple view geometry Stereo vision Epipolar geometry Lowe Hartley and Zisserman Depth map extraction Essential matrix

More information

Face Hallucination Based on Eigentransformation Learning

Face Hallucination Based on Eigentransformation Learning Advanced Science and Technology etters, pp.32-37 http://dx.doi.org/10.14257/astl.2016. Face allucination Based on Eigentransformation earning Guohua Zou School of software, East China University of Technology,

More information

A Survey On Super Resolution Image Reconstruction Techniques

A Survey On Super Resolution Image Reconstruction Techniques A Survey On Super Resolution Image Reconstruction Techniques Krunal Shah Jaymit Pandya Safvan Vahora Dept. of Info Tech,GCET Dept. of Info Tech,GCET Dept. of Info Tech,VGEC Engg.College, VV Nagar, Engg,College,VV

More information

Resolution. Super-Resolution Imaging. Problem

Resolution. Super-Resolution Imaging. Problem Resolution Super-Resolution Iaging Resolution: Sallest easurable detail in a visual presentation Subhasis Chaudhuri Departent of Electrical Engineering Indian institute of Technology Bobay Powai, Mubai-400

More information

Single and Multi-view Video Super-resolution

Single and Multi-view Video Super-resolution Single and Multi-view Video Super-resolution SINGLE AND MULTI-VIEW VIDEO SUPER-RESOLUTION BY SEYEDREZA NAJAFI, M.Sc. a thesis submitted to the department of electrical & computer engineering and the school

More information

Generalizing the Non-Local-Means to Super-resolution Reconstruction

Generalizing the Non-Local-Means to Super-resolution Reconstruction Generalizing the Non-Local-Means to Super-resolution Reconstruction M. Protter & M. Elad H. Takeda & P. Milanfar Department of Computer Science Department of Electrical Engineering Technion Israel Institute

More information

Locally Weighted Least Squares Regression for Image Denoising, Reconstruction and Up-sampling

Locally Weighted Least Squares Regression for Image Denoising, Reconstruction and Up-sampling Locally Weighted Least Squares Regression for Image Denoising, Reconstruction and Up-sampling Moritz Baecher May 15, 29 1 Introduction Edge-preserving smoothing and super-resolution are classic and important

More information

CS 4495 Computer Vision Motion and Optic Flow

CS 4495 Computer Vision Motion and Optic Flow CS 4495 Computer Vision Aaron Bobick School of Interactive Computing Administrivia PS4 is out, due Sunday Oct 27 th. All relevant lectures posted Details about Problem Set: You may *not* use built in Harris

More information

Edges, interpolation, templates. Nuno Vasconcelos ECE Department, UCSD (with thanks to David Forsyth)

Edges, interpolation, templates. Nuno Vasconcelos ECE Department, UCSD (with thanks to David Forsyth) Edges, interpolation, templates Nuno Vasconcelos ECE Department, UCSD (with thanks to David Forsyth) Edge detection edge detection has many applications in image processing an edge detector implements

More information

Image Reconstruction from Videos Distorted by Atmospheric Turbulence

Image Reconstruction from Videos Distorted by Atmospheric Turbulence Image Reconstruction from Videos Distorted by Atmospheric Turbulence Xiang Zhu and Peyman Milanfar Electrical Engineering Department University of California at Santa Cruz, CA, 95064 xzhu@soe.ucsc.edu

More information

Chapter 18. Geometric Operations

Chapter 18. Geometric Operations Chapter 18 Geometric Operations To this point, the image processing operations have computed the gray value (digital count) of the output image pixel based on the gray values of one or more input pixels;

More information

Ultrasound Speckle Reduction via Super Resolution and Nonlinear Diffusion

Ultrasound Speckle Reduction via Super Resolution and Nonlinear Diffusion Ultrasound Specle Reduction via Super Resolution and onlinear Diffusion Bo Wang, ian Cao, Yuguo Dai, and Dong C. Liu, Computer Science College, Sichuan University, China, 60064 {bowanghaw, ct.radiate,

More information

Theoretically Perfect Sensor

Theoretically Perfect Sensor Sampling 1/67 Sampling The ray tracer samples the geometry, only gathering information from the parts of the world that interact with a finite number of rays In contrast, a scanline renderer can push all

More information

Single Image Improvement using Superresolution.

Single Image Improvement using Superresolution. Single Image Improvement using Superresolution. ABSTRACT Shwetambari Shinde, Meeta Dewangan Department of Computer Science & Engineering,CSIT,Bhilai,India. shweta_shinde9388@yahoo Department of Computer

More information

Motion Estimation. There are three main types (or applications) of motion estimation:

Motion Estimation. There are three main types (or applications) of motion estimation: Members: D91922016 朱威達 R93922010 林聖凱 R93922044 謝俊瑋 Motion Estimation There are three main types (or applications) of motion estimation: Parametric motion (image alignment) The main idea of parametric motion

More information

Estimation of common groundplane based on co-motion statistics

Estimation of common groundplane based on co-motion statistics Estimation of common groundplane based on co-motion statistics Zoltan Szlavik, Laszlo Havasi 2, Tamas Sziranyi Analogical and Neural Computing Laboratory, Computer and Automation Research Institute of

More information

Single Image Super-resolution using Deformable Patches

Single Image Super-resolution using Deformable Patches Single Image Super-resolution using Deformable Patches Yu Zhu 1, Yanning Zhang 1, Alan L. Yuille 2 1 School of Computer Science, Northwestern Polytechnical University, China 2 Department of Statistics,

More information

Local Image Registration: An Adaptive Filtering Framework

Local Image Registration: An Adaptive Filtering Framework Local Image Registration: An Adaptive Filtering Framework Gulcin Caner a,a.murattekalp a,b, Gaurav Sharma a and Wendi Heinzelman a a Electrical and Computer Engineering Dept.,University of Rochester, Rochester,

More information

Influence of Training Set and Iterative Back Projection on Example-based Super-resolution

Influence of Training Set and Iterative Back Projection on Example-based Super-resolution Influence of Training Set and Iterative Back Projection on Example-based Super-resolution Saeid Fazli Research Institute of Modern Biological Techniques University of zanjan Zanjan, Iran Abstract Example-based

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

Image warping and stitching

Image warping and stitching Image warping and stitching May 4 th, 2017 Yong Jae Lee UC Davis Last time Interactive segmentation Feature-based alignment 2D transformations Affine fit RANSAC 2 Alignment problem In alignment, we will

More information

Targil 10 : Why Mosaic? Why is this a challenge? Exposure differences Scene illumination Miss-registration Moving objects

Targil 10 : Why Mosaic? Why is this a challenge? Exposure differences Scene illumination Miss-registration Moving objects Why Mosaic? Are you getting the whole picture? Compact Camera FOV = 5 x 35 Targil : Panoramas - Stitching and Blending Some slides from Alexei Efros 2 Slide from Brown & Lowe Why Mosaic? Are you getting

More information

Reconstructing Images of Bar Codes for Construction Site Object Recognition 1

Reconstructing Images of Bar Codes for Construction Site Object Recognition 1 Reconstructing Images of Bar Codes for Construction Site Object Recognition 1 by David E. Gilsinn 2, Geraldine S. Cheok 3, Dianne P. O Leary 4 ABSTRACT: This paper discusses a general approach to reconstructing

More information

Image Processing. Filtering. Slide 1

Image Processing. Filtering. Slide 1 Image Processing Filtering Slide 1 Preliminary Image generation Original Noise Image restoration Result Slide 2 Preliminary Classic application: denoising However: Denoising is much more than a simple

More information

Some Blind Deconvolution Techniques in Image Processing

Some Blind Deconvolution Techniques in Image Processing Some Blind Deconvolution Techniques in Image Processing Tony Chan Math Dept., UCLA Joint work with Frederick Park and Andy M. Yip IPAM Workshop on Mathematical Challenges in Astronomical Imaging July 26-30,

More information

Motivation. The main goal of Computer Graphics is to generate 2D images. 2D images are continuous 2D functions (or signals)

Motivation. The main goal of Computer Graphics is to generate 2D images. 2D images are continuous 2D functions (or signals) Motivation The main goal of Computer Graphics is to generate 2D images 2D images are continuous 2D functions (or signals) monochrome f(x,y) or color r(x,y), g(x,y), b(x,y) These functions are represented

More information

Theoretically Perfect Sensor

Theoretically Perfect Sensor Sampling 1/60 Sampling The ray tracer samples the geometry, only gathering information from the parts of the world that interact with a finite number of rays In contrast, a scanline renderer can push all

More information

EE 264: Image Processing and Reconstruction. Image Motion Estimation I. EE 264: Image Processing and Reconstruction. Outline

EE 264: Image Processing and Reconstruction. Image Motion Estimation I. EE 264: Image Processing and Reconstruction. Outline 1 Image Motion Estimation I 2 Outline 1. Introduction to Motion 2. Why Estimate Motion? 3. Global vs. Local Motion 4. Block Motion Estimation 5. Optical Flow Estimation Basics 6. Optical Flow Estimation

More information

Multiple Model Estimation : The EM Algorithm & Applications

Multiple Model Estimation : The EM Algorithm & Applications Multiple Model Estimation : The EM Algorithm & Applications Princeton University COS 429 Lecture Dec. 4, 2008 Harpreet S. Sawhney hsawhney@sarnoff.com Plan IBR / Rendering applications of motion / pose

More information

Image Super-Resolution via Sparse Representation

Image Super-Resolution via Sparse Representation Image Super-Resolution via Sparse Representation Jianchao Yang, John Wright, Thomas Huang and Yi Ma accepted by IEEE Trans. on Image Processing 2010 Presented by known 2010/4/20 1 Super-Resolution Techniques

More information

CS5670: Computer Vision

CS5670: Computer Vision CS5670: Computer Vision Noah Snavely Lecture 4: Harris corner detection Szeliski: 4.1 Reading Announcements Project 1 (Hybrid Images) code due next Wednesday, Feb 14, by 11:59pm Artifacts due Friday, Feb

More information

EE795: Computer Vision and Intelligent Systems

EE795: Computer Vision and Intelligent Systems EE795: Computer Vision and Intelligent Systems Spring 2012 TTh 17:30-18:45 FDH 204 Lecture 10 130221 http://www.ee.unlv.edu/~b1morris/ecg795/ 2 Outline Review Canny Edge Detector Hough Transform Feature-Based

More information

Single Image Super-Resolution

Single Image Super-Resolution Single Image Super-Resolution Abhishek Arora Dept. of Electrical Engg. Stanford University, CA Email: arorabhi@stanford.edu Ritesh Kolte Dept. of Electrical Engg. Stanford University, CA Email: rkolte@stanford.edu

More information

Imaging and Deconvolution

Imaging and Deconvolution Imaging and Deconvolution Urvashi Rau National Radio Astronomy Observatory, Socorro, NM, USA The van-cittert Zernike theorem Ei E V ij u, v = I l, m e sky j 2 i ul vm dldm 2D Fourier transform : Image

More information

Superresolution Using Preconditioned Conjugate Gradient Method

Superresolution Using Preconditioned Conjugate Gradient Method Superresolution Using Preconditioned Conjugate Gradient Method Changjiang Yang, Ramani Duraiswami and Larry Davis Computer Vision Laboratory University of Maryland, College Park, MD 20742 E-mail: {yangcj,ramani,lsd}@umiacs.umd.edu

More information

The main goal of Computer Graphics is to generate 2D images 2D images are continuous 2D functions (or signals)

The main goal of Computer Graphics is to generate 2D images 2D images are continuous 2D functions (or signals) Motivation The main goal of Computer Graphics is to generate 2D images 2D images are continuous 2D functions (or signals) monochrome f(x,y) or color r(x,y), g(x,y), b(x,y) These functions are represented

More information

Stereo imaging ideal geometry

Stereo imaging ideal geometry Stereo imaging ideal geometry (X,Y,Z) Z f (x L,y L ) f (x R,y R ) Optical axes are parallel Optical axes separated by baseline, b. Line connecting lens centers is perpendicular to the optical axis, and

More information

Panoramic Image Stitching

Panoramic Image Stitching Mcgill University Panoramic Image Stitching by Kai Wang Pengbo Li A report submitted in fulfillment for the COMP 558 Final project in the Faculty of Computer Science April 2013 Mcgill University Abstract

More information

Multi-frame super-resolution with no explicit motion estimation

Multi-frame super-resolution with no explicit motion estimation Multi-frame super-resolution with no explicit motion estimation Mehran Ebrahimi and Edward R. Vrscay Department of Applied Mathematics Faculty of Mathematics, University of Waterloo Waterloo, Ontario,

More information

Multiple Model Estimation : The EM Algorithm & Applications

Multiple Model Estimation : The EM Algorithm & Applications Multiple Model Estimation : The EM Algorithm & Applications Princeton University COS 429 Lecture Nov. 13, 2007 Harpreet S. Sawhney hsawhney@sarnoff.com Recapitulation Problem of motion estimation Parametric

More information

Image warping and stitching

Image warping and stitching Image warping and stitching May 5 th, 2015 Yong Jae Lee UC Davis PS2 due next Friday Announcements 2 Last time Interactive segmentation Feature-based alignment 2D transformations Affine fit RANSAC 3 Alignment

More information

Edge detection. Convert a 2D image into a set of curves. Extracts salient features of the scene More compact than pixels

Edge detection. Convert a 2D image into a set of curves. Extracts salient features of the scene More compact than pixels Edge Detection Edge detection Convert a 2D image into a set of curves Extracts salient features of the scene More compact than pixels Origin of Edges surface normal discontinuity depth discontinuity surface

More information

ZOOM-BASED SUPER-RESOLUTION IMAGE RECONSTRUCTION FROM IMAGES WITH DIFFERENT ORIENTATIONS. A Thesis by. Chandana K.K. Jayasooriya

ZOOM-BASED SUPER-RESOLUTION IMAGE RECONSTRUCTION FROM IMAGES WITH DIFFERENT ORIENTATIONS. A Thesis by. Chandana K.K. Jayasooriya ZOOM-BASED SUPER-RESOLUTION IMAGE RECONSTRUCTION FROM IMAGES WITH DIFFERENT ORIENTATIONS A Thesis by Chandana K.K. Jayasooriya Diplom in Electrical & Communications Engineering Technical University of

More information

Visual Tracking (1) Tracking of Feature Points and Planar Rigid Objects

Visual Tracking (1) Tracking of Feature Points and Planar Rigid Objects Intelligent Control Systems Visual Tracking (1) Tracking of Feature Points and Planar Rigid Objects Shingo Kagami Graduate School of Information Sciences, Tohoku University swk(at)ic.is.tohoku.ac.jp http://www.ic.is.tohoku.ac.jp/ja/swk/

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

Sampling, Aliasing, & Mipmaps

Sampling, Aliasing, & Mipmaps Last Time? Sampling, Aliasing, & Mipmaps 2D Texture Mapping Perspective Correct Interpolation Common Texture Coordinate Projections Bump Mapping Displacement Mapping Environment Mapping Texture Maps for

More information

Dense 3D Reconstruction. Christiano Gava

Dense 3D Reconstruction. Christiano Gava Dense 3D Reconstruction Christiano Gava christiano.gava@dfki.de Outline Previous lecture: structure and motion II Structure and motion loop Triangulation Wide baseline matching (SIFT) Today: dense 3D reconstruction

More information

Announcements. Mosaics. Image Mosaics. How to do it? Basic Procedure Take a sequence of images from the same position =

Announcements. Mosaics. Image Mosaics. How to do it? Basic Procedure Take a sequence of images from the same position = Announcements Project 2 out today panorama signup help session at end of class Today mosaic recap blending Mosaics Full screen panoramas (cubic): http://www.panoramas.dk/ Mars: http://www.panoramas.dk/fullscreen3/f2_mars97.html

More information

Super-Resolution from a Single Image

Super-Resolution from a Single Image Super-Resolution from a Single Image Daniel Glasner Shai Bagon Michal Irani Dept. of Computer Science and Applied Mathematics The Weizmann Institute of Science Rehovot 76100, Israel Abstract Methods for

More information

EECS 556 Image Processing W 09

EECS 556 Image Processing W 09 EECS 556 Image Processing W 09 Motion estimation Global vs. Local Motion Block Motion Estimation Optical Flow Estimation (normal equation) Man slides of this lecture are courtes of prof Milanfar (UCSC)

More information

Sparse Representation Based Super-Resolution Algorithm using Wavelet Domain Interpolation and Nonlocal Means

Sparse Representation Based Super-Resolution Algorithm using Wavelet Domain Interpolation and Nonlocal Means TELKOMNIKA Indonesian Journal of Electrical Engineering Vol. 16, No. 2, November 2015, pp. 296 ~ 302 DOI: 10.11591/telkomnika.v16i2.8816 296 Sparse Representation Based Super-Resolution Algorithm using

More information

Aliasing. Can t draw smooth lines on discrete raster device get staircased lines ( jaggies ):

Aliasing. Can t draw smooth lines on discrete raster device get staircased lines ( jaggies ): (Anti)Aliasing and Image Manipulation for (y = 0; y < Size; y++) { for (x = 0; x < Size; x++) { Image[x][y] = 7 + 8 * sin((sqr(x Size) + SQR(y Size)) / 3.0); } } // Size = Size / ; Aliasing Can t draw

More information

Video Super Resolution using Duality Based TV-L 1 Optical Flow

Video Super Resolution using Duality Based TV-L 1 Optical Flow Video Super Resolution using Duality Based TV-L 1 Optical Flow Dennis Mitzel 1,2, Thomas Pock 3, Thomas Schoenemann 1 Daniel Cremers 1 1 Department of Computer Science University of Bonn, Germany 2 UMIC

More information

NEW TECHNIQUES TO CONQUER THE IMAGE RESOLUTION ENHANCEMENT PROBLEM

NEW TECHNIQUES TO CONQUER THE IMAGE RESOLUTION ENHANCEMENT PROBLEM Progress In Electromagnetics Research B, Vol. 7, 13 51, 2008 NEW TECHNIQUES TO CONQUER THE IMAGE RESOLUTION ENHANCEMENT PROBLEM S. E. El-Khamy Department of Electrical Engineering Faculty of Engineering

More information

A Fast Image Super-Resolution Algorithm Using an Adaptive Wiener Filter

A Fast Image Super-Resolution Algorithm Using an Adaptive Wiener Filter University of Dayton ecommons Electrical and Computer Engineering Faculty Publications Department of Electrical and Computer Engineering 12-2007 A Fast Image Super-Resolution Algorithm Using an Adaptive

More information

convolution shift invariant linear system Fourier Transform Aliasing and sampling scale representation edge detection corner detection

convolution shift invariant linear system Fourier Transform Aliasing and sampling scale representation edge detection corner detection COS 429: COMPUTER VISON Linear Filters and Edge Detection convolution shift invariant linear system Fourier Transform Aliasing and sampling scale representation edge detection corner detection Reading:

More information

Anchored Neighborhood Regression for Fast Example-Based Super-Resolution

Anchored Neighborhood Regression for Fast Example-Based Super-Resolution Anchored Neighborhood Regression for Fast Example-Based Super-Resolution Radu Timofte 1,2, Vincent De Smet 1, and Luc Van Gool 1,2 1 KU Leuven, ESAT-PSI / iminds, VISICS 2 ETH Zurich, D-ITET, Computer

More information

CPSC 4040/6040 Computer Graphics Images. Joshua Levine

CPSC 4040/6040 Computer Graphics Images. Joshua Levine CPSC 4040/6040 Computer Graphics Images Joshua Levine levinej@clemson.edu Lecture 19 Projective Warping and Bilinear Warping Nov. 3, 2015 Agenda EC Quiz Review PA06 out Refresher from Lec18 https://en.wikipedia.org/wiki/affine_transformation

More information

Ping Tan. Simon Fraser University

Ping Tan. Simon Fraser University Ping Tan Simon Fraser University Photos vs. Videos (live photos) A good photo tells a story Stories are better told in videos Videos in the Mobile Era (mobile & share) More videos are captured by mobile

More information

Broad field that includes low-level operations as well as complex high-level algorithms

Broad field that includes low-level operations as well as complex high-level algorithms Image processing About Broad field that includes low-level operations as well as complex high-level algorithms Low-level image processing Computer vision Computational photography Several procedures and

More information

Structured Light II. Thanks to Ronen Gvili, Szymon Rusinkiewicz and Maks Ovsjanikov

Structured Light II. Thanks to Ronen Gvili, Szymon Rusinkiewicz and Maks Ovsjanikov Structured Light II Johannes Köhler Johannes.koehler@dfki.de Thanks to Ronen Gvili, Szymon Rusinkiewicz and Maks Ovsjanikov Introduction Previous lecture: Structured Light I Active Scanning Camera/emitter

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 3. HIGH DYNAMIC RANGE Computer Vision 2 Dr. Benjamin Guthier Pixel Value Content of this

More information

Matching. Compare region of image to region of image. Today, simplest kind of matching. Intensities similar.

Matching. Compare region of image to region of image. Today, simplest kind of matching. Intensities similar. Matching Compare region of image to region of image. We talked about this for stereo. Important for motion. Epipolar constraint unknown. But motion small. Recognition Find object in image. Recognize object.

More information

Index. 3D reconstruction, point algorithm, point algorithm, point algorithm, point algorithm, 253

Index. 3D reconstruction, point algorithm, point algorithm, point algorithm, point algorithm, 253 Index 3D reconstruction, 123 5+1-point algorithm, 274 5-point algorithm, 260 7-point algorithm, 255 8-point algorithm, 253 affine point, 43 affine transformation, 55 affine transformation group, 55 affine

More information

Dense 3D Reconstruction. Christiano Gava

Dense 3D Reconstruction. Christiano Gava Dense 3D Reconstruction Christiano Gava christiano.gava@dfki.de Outline Previous lecture: structure and motion II Structure and motion loop Triangulation Today: dense 3D reconstruction The matching problem

More information