Image Warping. Image Manipula-on and Computa-onal Photography CS Fall 2011 Robert Carroll.

Size: px
Start display at page:

Download "Image Warping. Image Manipula-on and Computa-onal Photography CS Fall 2011 Robert Carroll."

Transcription

1 Image Warping Image Manipula-on and Computa-onal Photography CS Fall 2011 Robert Carroll [Some slides from K. Padalkar, S. Avidan, A. Shamir, A. Efros, S. Seitz, and Y. Wang]

2 What is a warp?

3 Original What is a warp?

4 What is a warp? Original Warped Warps are spatial transformations: Points map to points, but colors don t change.

5 Applications Panorama Stitching Resizing/Retargeting Wide-Angle Distortion Shape Manipulation [Igarashi et al. 09] Video Stabilization, Stereoscopic Depth Editing, Object Removal,...

6 Applications Panorama Stitching Resizing/Retargeting Wide-Angle Distortion Shape Manipulation [Igarashi et al. 09] Video Stabilization, Stereoscopic Depth Editing, Object Removal,...

7 Image Transformations image filtering: change range of image g(x) = T(f(x)) f T f x image warping: change domain of image x f g(x) = f(t(x)) T f x x

8 Image Transformations image filtering: change range of image g(x) = T(f(x)) f T g image warping: change domain of image f g(x) = f(t(x)) T g

9 Types of Warps Parametric: - Globally defined by small # of parameters rotation aspect perspective cylindrical Mesh: - Smooth (rubber sheet) transformaaon [Wang et al. 09] Discrete: - Each output pixel can be an arbitrary input pixel [Barnes et al. 09]

10 The Image Resizing/RetargeAng Problem

11 The Image Resizing/RetargeAng Problem

12 Image Retarge-ng Objec-ves 1. Change size 2. Preserve the important content and structures 3. Limit ar*facts created

13 Tradi-onal Methods original squeeze crop hybrid letterbox Letterbox wastes pixels Squeeze/Hybrid introduce distortions Cropping removes important parts

14 Many Exis-ng Resizing Methods

15 Seam Carving for Content-Aware Image Resizing Shai Avidan and Ariel Shamir, Proc. SIGGRAPH, 2007

16 Seam Carving Method

17 Seam Carving Method Seam Carving for Content- Aware Image Resizing, S. Avidan and A. Shamir, Proc. SIGGRAPH, 2007

18 Seam Carving Method Seam Carving for Content- Aware Image Resizing, S. Avidan and A. Shamir, Proc. SIGGRAPH, 2007 In Photoshop called content aware scaling

19 Seam Carving Method Seam Carving for Content- Aware Image Resizing, S. Avidan and A. Shamir, Proc. SIGGRAPH, 2007 In Photoshop called content aware scaling Main idea: Remove the least nohceable pixels How? Define an energy func-on that measures how perceptually no-ceable each pixel is

20 Seam Carving Method Seam Carving for Content- Aware Image Resizing, S. Avidan and A. Shamir, Proc. SIGGRAPH, 2007 In Photoshop called content aware scaling Main idea: Remove the least nohceable pixels How? Define an energy func-on that measures how perceptually no-ceable each pixel is Remove the pixels with low energy and avoid removing pixels with high energy How? Define a criterion for picking which pixels to remove

21 Possible Energy Func-ons Edgeness Gradient magnitude Entropy HOG (Histogram of Gradient) Saliency Caveat: No single energy function performs well across all images

22 Possible Energy Func-ons Edgeness Gradient magnitude Entropy HOG (Histogram of Gradient) Saliency Caveat: No single energy function performs well across all images

23 Pixel Removal Criteria Op#mal: remove the k pixels with lowest energy Output image no longer rectangular Input image Energy image Output image

24 Pixel Removal Criteria Remove k pixels with lowest energy in each row No visual coherence between adjacent rows

25 Pixel Removal Criteria Column: Remove whole column with lowest energy Frequently introduces arhfacts

26 Seam Defini-on

27 VerAcal Seam Seam Defini-on is an 8- connected path of pixels in an n x m image from top to boqom, containing one, and only one, pixel in each row of the image:

28 VerAcal Seam Seam Defini-on is an 8- connected path of pixels in an n x m image from top to boqom, containing one, and only one, pixel in each row of the image:

29 VerAcal Seam Seam Defini-on is an 8- connected path of pixels in an n x m image from top to boqom, containing one, and only one, pixel in each row of the image:

30 Seam Energy Energy of a Seam Minimum Energy Seam

31 Pixel Removal Criteria Seam: Remove the verhcal curve of lowest energy

32 Pixel Removal Effec-veness

33 How to Efficiently Compute Best Seam? Use Dynamic Programming to find lowest energy seam in linear Hme 1. Forward Pass (top row to bowom row for finding verhcal seam) Define M(i,j) = cumula-ve energy at (i,j) M(1,j) = e(1,j) M(i,j) = e(i,j) + min(m(i- 1,j- 1), M(i- 1,j), M(i- 1, j+1)) Find minimum value in last row: min j M(n,j) 2. Backward Pass (bowom row to top row) Trace back path from pixel in bozom row with min value to top row

34 Seams Seams over energy image Seams over input image

35 Shrink Image in 1 Dimension

36 Shrink Image in 1 Dimension Change the image from size n m to n mʹ assume mʹ < m

37 Shrink Image in 1 Dimension Change the image from size n m to n mʹ assume mʹ < m Remove m- mʹ = c seams successively

38 Shrink Image in 1 Dimension Change the image from size n m to n mʹ assume mʹ < m Remove m- mʹ = c seams successively

39 Shrink Image in 1 Dimension Change the image from size n m to n mʹ assume mʹ < m Remove m- mʹ = c seams successively Seam Carving

40 Shrink Image in 1 Dimension Change the image from size n m to n mʹ assume mʹ < m Remove m- mʹ = c seams successively Scaling

41 Shrink Image in Both Dimensions: Op-mal Seam Ordering

42 Shrink Image in Both Dimensions: Op-mal Seam Ordering Change the image from size n m to nʹ mʹ assume mʹ < m and nʹ < n

43 Shrink Image in Both Dimensions: Op-mal Seam Ordering Change the image from size n m to nʹ mʹ assume mʹ < m and nʹ < n What is the best order for seam carving? Remove verhcal seams first? Horizontal seams first? Alternate between the two?

44 Op-mal Seam Ordering

45 Op-mal Seam Ordering Solve ophmizahon problem:

46 Op-mal Seam Ordering Solve ophmizahon problem:

47 Op-mal Seam Ordering Solve ophmizahon problem: where k = r+c, r = (m mʹ ), c = (n nʹ ) and α i is a parameter that determines if at step i we remove a horizontal or veracal seam: α {0,1}

48 Op-mal Seam Ordering

49 Op-mal Seam Ordering Transport map Matrix of size n m Each element T(r,c) holds the minimal cost needed to obtain an image of size n r m c

50 Op-mal Seam Ordering Transport map Matrix of size n m Each element T(r,c) holds the minimal cost needed to obtain an image of size n r m c

51 Enlarging Images

52 Enlarging Images Method 1: Compute the opamal veracal (horizontal) seam s in image and duplicate the pixels in s by averaging them with their le` and right neighbors (top and boqom in the horizontal case) O`en will choose the same seam at each iteraaon, producing noaceable stretching arafact

53 Enlarging Images Method 1: Compute the opamal veracal (horizontal) seam s in image and duplicate the pixels in s by averaging them with their le` and right neighbors (top and boqom in the horizontal case) O`en will choose the same seam at each iteraaon, producing noaceable stretching arafact

54 Enlarging Images Method 1: Compute the opamal veracal (horizontal) seam s in image and duplicate the pixels in s by averaging them with their le` and right neighbors (top and boqom in the horizontal case) O`en will choose the same seam at each iteraaon, producing noaceable stretching arafact

55 Enlarging Images Method 2: To enlarge width by k, compute top k veracal seams (for removal) and duplicate each of them

56 Content Amplifica-on

57 Content Amplifica-on Scale the image; this will scale everything, content as well as non- content Shrink the scaled- image using seam carving, which will (hopefully) carve out the non- content part

58 Content Amplifica-on Scale the image; this will scale everything, content as well as non- content Shrink the scaled- image using seam carving, which will (hopefully) carve out the non- content part

59 Content Amplifica-on Scale the image; this will scale everything, content as well as non- content Shrink the scaled- image using seam carving, which will (hopefully) carve out the non- content part

60 Object Removal

61 Object Removal User marks the target object to be removed Force seams to pass through marked pixels To obtain the original image size, use seam inseraon

62 Object Removal User marks the target object to be removed Force seams to pass through marked pixels To obtain the original image size, use seam inseraon

63 Object Removal User marks the target object to be removed Force seams to pass through marked pixels To obtain the original image size, use seam inseraon

64 Object Removal One shoe removed (and image enlarged to original size) input result

65 Object Removal Object marking to prevent unwanted results: mark regions where seams must not pass

66 Object Removal Object marking to prevent unwanted results: mark regions where seams must not pass

67 Object Removal Object marking to prevent unwanted results: mark regions where seams must not pass

68 Object Removal Object marking to prevent unwanted results: mark regions where seams must not pass

69 Mul-- Size Images Input H V

70 Mul-- Size Images Methods menaoned so far are not real- Ame Input H V

71 Mul-- Size Images Methods menaoned so far are not real- Ame We calculate best seam, remove it, calculate the next seam based on new image, etc. Input H V

72 Mul-- Size Images Methods menaoned so far are not real- Ame We calculate best seam, remove it, calculate the next seam based on new image, etc. Compute Index map, V, of size n m that encodes, for each pixel, the index of the seam that removed it, i.e., V(i, j) = t means pixel (i, j) was removed by the t th seam removal iteraaon Input H V

73 Failures Too much content No space for seam to avoid content

74 Optimized Scale-and-Stretch for Image Resizing 1 Yu-Shuen Wang, 2 Chiew-Lan Tai, 3 Olga Sorkine, 1 Tong-Yee Lee 1 National Cheng Kung University, Taiwan 2 Hong Kong University of Science & Technology 3 New York University

75 Scale-and-stretch warp Allow important regions to uniformly scale Find optimal local scaling factors by global optimization Result: preserve the shape of important regions, distort non-important ones importance map

76 Importance map x = saliency map [Itti et al. 98] importance map gradients only importance map

77 The warping mechanism Grid mesh, preserve the shape of the important quads quads with high importance uniform scaling quads with low importance allow non-uniform scaling Optimize the location of mesh vertices, interpolate image

78 The warping mechanism Grid mesh, preserve the shape of the important quads Optimize the location of mesh vertices, interpolate image

79 Deformation Energy Per quad vʹ i v i f vʹ j v j s f uniform scaling

80 Deformation Energy Total deformation energy importance weights Quadratic energy in vʹ, can minimize by solving a linear system of equations

81 Constraints Corner vertices Horizontal/vertical sliding

82 Deformation energy Problem: grid lines bend a lot; warp not so smooth

83 Deformation energy Problem: grid lines bend a lot; warp not so smooth

84 Grid line bending energy Attempt to keep original edge orientations but allow length scaling note the nonlinear factor f v i vʹ i v j vʹ j

85 Energy minimization Total energy is nonlinear in vʹ Iterative minimization with tricks Keep s f and l ij as additional variables Do alternating minimization steps Fix s f and l ij and optimize vʹ Compute new s f and l ij Sparse direct solver for the linear system and reuse the matrix factorization to gain speed.

86 Grid line bending energy With the bending term added

87 Results

88 Results original SC indirect SC Mesh can move in 2D, with seam carving pixels only move in 1D Scale-and-Stretch

89 Results original SC indirect SC Scale-and-Stretch

90 Results original SC indirect SC Scale-and-Stretch

91 Optimizing Content-Preserving Projections for Wide-Angle Images Robert Carroll Maneesh Agrawala University of California, Berkeley Aseem Agarwala Adobe Systems, Inc.

92 Rectilinear Lens Keith Cooper

93 Fisheye Flickr user kirainet

94 Cylindrical Panorama Flickr user Seb Przd

95

96 Viewing Sphere

97 Viewing Sphere

98 Viewing Sphere

99 Viewing Sphere

100 Courtesy of Flickr user brokendrum70 Cartography

101

102 Linear Perspective Projection

103 Linear Perspective Projection

104 Stereographic Projection

105 Stereographic Projection

106 Cylindrical Projection

107 Mercator Projection

108 Optimized Projection

109 Optimized Projection

110 Goal Given a wide-angle image, produce a projection that preserves straight lines in the scene and the shapes of objects

111

112 Our Approach Mesh the viewing sphere Define mapping constraints Optimize weighted energy function

113 Viewing Sphere Mesh

114 Viewing Sphere Mesh

115 Viewing Sphere Mesh

116 Viewing Sphere Mesh

117 Three Properties 1. Conformality 2. Straight Lines 3. Smoothness of mapping

118 Conformality h k

119 Conformality h k

120 Lines

121 Lines

122 Lines Should be zero

123 Lines Should be zero

124 Lines Should be zero

125 Smoothness

126 Smoothness

127 Smoothness

128 Smoothness

129 What s left? Cannot satisfy all constraints exactly Define weighted least-squares energy terms E total = w 1 E conformality + w 2 E lines + w 3 E smoothness Iterative non-linear optimization

130 Lines Should be zero

131 Lines Should be zero

132 Lines Should be zero

133 Lines fixed n

134 Lines fixed n

135 Lines (1 ) Should be zero

136 Lines fixed

137 Lines fixed

138 Lines fixed n

139 Lines fixed n

140 Lines fixed

141 Lines fixed

142 Implementation Details Converges in 8 iterations Up to 160,000 vertices 15s - 1m, depending on field of view

143 Results

144 Input/Output

145 Input/Output

146 Perspective Mercator Stereographic Our Result

147

148 Perspective Mercator Stereographic Our Result

149

150 Perspective Mercator Stereographic Our Result

151 Image Courtesy Flickr user Aldo

152 Perspective Mercator Stereographic Our Result

153 Image Courtesy Jeff Chien

154 Perspective Mercator Stereographic Our Result

155 Input ( Flickr user Mike Schinkel) Zorin Our Result

156 Zelnik-Manor et al. MultiPlane Zelnik-Manor et al. MultiView Mercator Our Result

157 Zelnik-Manor et al. MultiPlane Zelnik-Manor et al. MultiView Mercator Our Result

158 Zelnik-Manor et al. MultiPlane Zelnik-Manor et al. MultiView Mercator Our Result

159 Must be cropped Limitations

160 Limitations Some stretching near poles

161 Limitations Some stretching near poles Geodesic Grid

162 Limitations Lines that stretch across the full field of view Flickr user Editor B

163 Thanks!

Rectangling Panoramic Images via Warping

Rectangling Panoramic Images via Warping Rectangling Panoramic Images via Warping Kaiming He Microsoft Research Asia Huiwen Chang Tsinghua University Jian Sun Microsoft Research Asia Introduction Panoramas are irregular Introduction Panoramas

More information

Seam-Carving. Michael Rubinstein MIT. and Content-driven Retargeting of Images (and Video) Some slides borrowed from Ariel Shamir and Shai Avidan

Seam-Carving. Michael Rubinstein MIT. and Content-driven Retargeting of Images (and Video) Some slides borrowed from Ariel Shamir and Shai Avidan Seam-Carving and Content-driven Retargeting of Images (and Video) Michael Rubinstein MIT Some slides borrowed from Ariel Shamir and Shai Avidan Display Devices Content Retargeting PC iphone Page Layout

More information

An Improved Image Resizing Approach with Protection of Main Objects

An Improved Image Resizing Approach with Protection of Main Objects An Improved Image Resizing Approach with Protection of Main Objects Chin-Chen Chang National United University, Miaoli 360, Taiwan. *Corresponding Author: Chun-Ju Chen National United University, Miaoli

More information

Image Compression and Resizing Using Improved Seam Carving for Retinal Images

Image Compression and Resizing Using Improved Seam Carving for Retinal Images Image Compression and Resizing Using Improved Seam Carving for Retinal Images Prabhu Nayak 1, Rajendra Chincholi 2, Dr.Kalpana Vanjerkhede 3 1 PG Student, Department of Electronics and Instrumentation

More information

Lecture #9: Image Resizing and Segmentation

Lecture #9: Image Resizing and Segmentation Lecture #9: Image Resizing and Segmentation Mason Swofford, Rachel Gardner, Yue Zhang, Shawn Fenerin Department of Computer Science Stanford University Stanford, CA 94305 {mswoff, rachel0, yzhang16, sfenerin}@cs.stanford.edu

More information

Content-Aware Image Resizing

Content-Aware Image Resizing Content-Aware Image Resizing EE368 Project Report Parnian Zargham Stanford University Electrical Engineering Department Stanford, CA pzargham@stanford.edu Sahar Nassirpour Stanford University Electrical

More information

Rectangling Stereographic Projection for Wide-Angle Image Visualization

Rectangling Stereographic Projection for Wide-Angle Image Visualization 2013 IEEE International Conference on Computer Vision Rectangling Stereographic Projection for Wide-Angle Image Visualization Che-Han Chang 1 Min-Chun Hu 2 Wen-Huang Cheng 3 Yung-Yu Chuang 1 1 National

More information

2.1 Optimized Importance Map

2.1 Optimized Importance Map 3rd International Conference on Multimedia Technology(ICMT 2013) Improved Image Resizing using Seam Carving and scaling Yan Zhang 1, Jonathan Z. Sun, Jingliang Peng Abstract. Seam Carving, the popular

More information

Advanced Computer Graphics

Advanced Computer Graphics G22.2274 001, Fall 2009 Advanced Computer Graphics Project details and tools 1 Project Topics Computer Animation Geometric Modeling Computational Photography Image processing 2 Optimization All projects

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

More Mosaic Madness. CS194: Image Manipulation & Computational Photography. Steve Seitz and Rick Szeliski. Jeffrey Martin (jeffrey-martin.

More Mosaic Madness. CS194: Image Manipulation & Computational Photography. Steve Seitz and Rick Szeliski. Jeffrey Martin (jeffrey-martin. More Mosaic Madness Jeffrey Martin (jeffrey-martin.com) CS194: Image Manipulation & Computational Photography with a lot of slides stolen from Alexei Efros, UC Berkeley, Fall 2018 Steve Seitz and Rick

More information

Image gradients and edges April 11 th, 2017

Image gradients and edges April 11 th, 2017 4//27 Image gradients and edges April th, 27 Yong Jae Lee UC Davis PS due this Friday Announcements Questions? 2 Last time Image formation Linear filters and convolution useful for Image smoothing, removing

More information

Image gradients and edges April 10 th, 2018

Image gradients and edges April 10 th, 2018 Image gradients and edges April th, 28 Yong Jae Lee UC Davis PS due this Friday Announcements Questions? 2 Last time Image formation Linear filters and convolution useful for Image smoothing, removing

More information

Visual Media Retargeting

Visual Media Retargeting Visual Media Retargeting Ariel Shamir The Interdisciplinary Center, Herzliya Olga Sorkine New York University operators. We will present several ways to define importance maps that use spatial information

More information

Scalable Motion-Aware Panoramic Videos

Scalable Motion-Aware Panoramic Videos Scalable Motion-Aware Panoramic Videos Leonardo Sacht Luiz Velho Diego Nehab Marcelo Cicconet IMPA, Rio de Janeiro, Brazil September 16, 2011 Abstract The work presents a method for obtaining perceptually

More information

Wook Kim. 14 September Korea University Computer Graphics Lab.

Wook Kim. 14 September Korea University Computer Graphics Lab. Wook Kim 14 September 2011 Preview - Seam carving How to choose the pixels to be removed? Remove unnoticeable pixels that blend with their surroundings. Wook, Kim 14 September 2011 # 2 Preview Energy term

More information

Advanced Computer Graphics

Advanced Computer Graphics G22.2274 001, Fall 2010 Advanced Computer Graphics Project details and tools 1 Projects Details of each project are on the website under Projects Please review all the projects and come see me if you would

More information

GPU Video Retargeting with Parallelized SeamCrop

GPU Video Retargeting with Parallelized SeamCrop GPU Video Retargeting with Parallelized SeamCrop Johannes Kiess, Daniel Gritzner, Benjamin Guthier Stephan Kopf, Wolfgang Effelsberg Department of Computer Science IV University of Mannheim, Mannheim,

More information

Image gradients and edges

Image gradients and edges Image gradients and edges April 7 th, 2015 Yong Jae Lee UC Davis Announcements PS0 due this Friday Questions? 2 Last time Image formation Linear filters and convolution useful for Image smoothing, removing

More information

Midterm Examination CS 534: Computational Photography

Midterm Examination CS 534: Computational Photography Midterm Examination CS 534: Computational Photography November 3, 2016 NAME: Problem Score Max Score 1 6 2 8 3 9 4 12 5 4 6 13 7 7 8 6 9 9 10 6 11 14 12 6 Total 100 1 of 8 1. [6] (a) [3] What camera setting(s)

More information

Shift-Map Image Editing

Shift-Map Image Editing Shift-Map Image Editing Yael Pritch Eitam Kav-Venaki Shmuel Peleg School of Computer Science and Engineering The Hebrew University of Jerusalem 91904 Jerusalem, Israel Abstract Geometric rearrangement

More information

Practical Image and Video Processing Using MATLAB

Practical Image and Video Processing Using MATLAB Practical Image and Video Processing Using MATLAB Chapter 7 Geometric operations What will we learn? What do geometric operations do to an image and what are they used for? What are the techniques used

More information

Geometric Modeling and Processing

Geometric Modeling and Processing Geometric Modeling and Processing Tutorial of 3DIM&PVT 2011 (Hangzhou, China) May 16, 2011 6. Mesh Simplification Problems High resolution meshes becoming increasingly available 3D active scanners Computer

More information

WITH the development of mobile devices, image retargeting

WITH the development of mobile devices, image retargeting IEEE TRANSACTIONS ON MULTIMEDIA, VOL. 15, NO. 2, FEBRUARY 2013 359 Patch-Based Image Warping for Content-Aware Retargeting Shih-Syun Lin, I-Cheng Yeh, Chao-Hung Lin, Member, IEEE, and Tong-Yee Lee, Senior

More information

Image Resizing Based on Gradient Vector Flow Analysis

Image Resizing Based on Gradient Vector Flow Analysis Image Resizing Based on Gradient Vector Flow Analysis Sebastiano Battiato battiato@dmi.unict.it Giovanni Puglisi puglisi@dmi.unict.it Giovanni Maria Farinella gfarinellao@dmi.unict.it Daniele Ravì rav@dmi.unict.it

More information

CONTENT BASED IMAGE COMPRESSION TECHNIQUES: A SURVEY

CONTENT BASED IMAGE COMPRESSION TECHNIQUES: A SURVEY CONTENT BASED IMAGE COMPRESSION TECHNIQUES: A SURVEY Salija.p, Manimekalai M.A.P, Dr.N.A Vasanti Abstract There are many image compression methods which compress the image as a whole and not considering

More information

Warping. 12 May 2015

Warping. 12 May 2015 Warping 12 May 2015 Warping, morphing, mosaic Slides from Durand and Freeman (MIT), Efros (CMU, Berkeley), Szeliski (MSR), Seitz (UW), Lowe (UBC) http://szeliski.org/book/ 2 Image Warping Image filtering:

More information

International Journal of Mechatronics, Electrical and Computer Technology

International Journal of Mechatronics, Electrical and Computer Technology An Efficient Importance Map for Content Aware Image Resizing Abstract Ahmad Absetan 1* and Mahdi Nooshyar 2 1 Faculty of Engineering, University of MohagheghArdabili, Ardabil, Iran 2 Faculty of Engineering,

More information

INTRODUCTION TO 360 VIDEO. Oliver Wang Adobe Research

INTRODUCTION TO 360 VIDEO. Oliver Wang Adobe Research INTRODUCTION TO 360 VIDEO Oliver Wang Adobe Research OUTLINE What is 360 video? OUTLINE What is 360 video? How do we represent it? Formats OUTLINE What is 360 video? How do we represent it? How do we create

More information

A Framework to Evaluate Omnidirectional Video Coding Schemes

A Framework to Evaluate Omnidirectional Video Coding Schemes 2015 IEEE International Symposium on Mixed and Augmented Reality A Framework to Evaluate Omnidirectional Video Coding Schemes Matt Yu Haricharan Lakshman Department of Electrical Engineering Stanford University

More information

Chapter 3 Image Registration. Chapter 3 Image Registration

Chapter 3 Image Registration. Chapter 3 Image Registration Chapter 3 Image Registration Distributed Algorithms for Introduction (1) Definition: Image Registration Input: 2 images of the same scene but taken from different perspectives Goal: Identify transformation

More information

N-Views (1) Homographies and Projection

N-Views (1) Homographies and Projection CS 4495 Computer Vision N-Views (1) Homographies and Projection Aaron Bobick School of Interactive Computing Administrivia PS 2: Get SDD and Normalized Correlation working for a given windows size say

More information

Image Retargeting for Small Display Devices

Image Retargeting for Small Display Devices Image Retargeting for Small Display Devices Chanho Jung and Changick Kim Department of Electrical Engineering Korea Advanced Institute of Science and Technology (KAIST) Daejeon, Republic of Korea ABSTRACT

More information

How to measure the relevance of a retargeting approach?

How to measure the relevance of a retargeting approach? How to measure the relevance of a retargeting approach? ECCV 10, Greece, 10 September 2010 Philippe Guillotel Philippe.guillotel@technicolor.com Christel Chamaret 1, Olivier Le Meur 2, Philippe Guillotel

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

Improved Seam Carving for Video Retargeting. By Erik Jorgensen, Margaret Murphy, and Aziza Saulebay

Improved Seam Carving for Video Retargeting. By Erik Jorgensen, Margaret Murphy, and Aziza Saulebay Improved Seam Carving for Video Retargeting By Erik Jorgensen, Margaret Murphy, and Aziza Saulebay CS 534 Fall 2015 Professor Dyer December 21, 2015 Table of Contents 1. Abstract.....3 2. Introduction.......3

More information

A Warping Framework for Wide-Angle Imaging and Perspective Manipulation

A Warping Framework for Wide-Angle Imaging and Perspective Manipulation A Warping Framework for Wide-Angle Imaging and Perspective Manipulation Robert Carroll Electrical Engineering and Computer Sciences University of California at Berkeley Technical Report No. UCB/EECS-2013-152

More information

Importance Filtering for Image Retargeting

Importance Filtering for Image Retargeting Importance Filtering for Image Retargeting Yuanyuan Ding Epson R&D, Inc. yding@erd.epson.com Jing Xiao Epson R&D, Inc. xiaoj@erd.epson.com Jingyi Yu University of Delaware yu@eecis.udel.edu Abstract Content-aware

More information

Content Aware Texture Compression

Content Aware Texture Compression JOURNAL OF INFORMATION SCIENCE AND ENGINEERING 31, 2075-2088 (2015) Content Aware Texture Compression Department of Computer Science National Chiao Tung University Hsinchu, 300 Taiwan E-mail: 22kinds@gmail.com;

More information

Efficient Depth-aware Image Deformation Adaptation for Curved Screen Displays

Efficient Depth-aware Image Deformation Adaptation for Curved Screen Displays Efficient Depth-aware Image Deformation Adaptation for Curved Screen Displays Shao-Ping Lu 1,2, Ruxandra-Marina Florea 1,2, Pablo Cesar 3,4, Peter Schelkens 1,2, Adrian Munteanu 1,2 1 Vrije Universiteit

More information

Parallel Computation of Spherical Parameterizations for Mesh Analysis. Th. Athanasiadis and I. Fudos University of Ioannina, Greece

Parallel Computation of Spherical Parameterizations for Mesh Analysis. Th. Athanasiadis and I. Fudos University of Ioannina, Greece Parallel Computation of Spherical Parameterizations for Mesh Analysis Th. Athanasiadis and I. Fudos, Greece Introduction Mesh parameterization is a powerful geometry processing tool Applications Remeshing

More information

Content-Aware Rotation

Content-Aware Rotation Content-Aware Rotation Kaiming He Microsoft Research Asia Huiwen Chang Tsinghua University Jian Sun Microsoft Research Asia Abstract We present an image editing tool called Content-Aware Rotation. Casually

More information

CSE 554 Lecture 7: Deformation II

CSE 554 Lecture 7: Deformation II CSE 554 Lecture 7: Deformation II Fall 2011 CSE554 Deformation II Slide 1 Review Rigid-body alignment Non-rigid deformation Intrinsic methods: deforming the boundary points An optimization problem Minimize

More information

CS 231A Computer Vision (Autumn 2012) Problem Set 1

CS 231A Computer Vision (Autumn 2012) Problem Set 1 CS 231A Computer Vision (Autumn 2012) Problem Set 1 Due: Oct. 9 th, 2012 (2:15 pm) 1 Finding an Approximate Image asis EigenFaces (25 points) In this problem you will implement a solution to a facial recognition

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

technique: seam carving Image and Video Processing Chapter 9

technique: seam carving Image and Video Processing Chapter 9 Chapter 9 Seam Carving for Images and Videos Distributed Algorithms for 2 Introduction Goals Enhance the visual content of images Adapted images should look natural Most relevant content should be clearly

More information

What have we leaned so far?

What have we leaned so far? What have we leaned so far? Camera structure Eye structure Project 1: High Dynamic Range Imaging What have we learned so far? Image Filtering Image Warping Camera Projection Model Project 2: Panoramic

More information

Image Blending and Compositing NASA

Image Blending and Compositing NASA Image Blending and Compositing NASA CS194: Image Manipulation & Computational Photography Alexei Efros, UC Berkeley, Fall 2016 Image Compositing Compositing Procedure 1. Extract Sprites (e.g using Intelligent

More information

Lecture 16: Computer Vision

Lecture 16: Computer Vision CS4442/9542b: Artificial Intelligence II Prof. Olga Veksler Lecture 16: Computer Vision Motion Slides are from Steve Seitz (UW), David Jacobs (UMD) Outline Motion Estimation Motion Field Optical Flow Field

More information

Lecture 16: Computer Vision

Lecture 16: Computer Vision CS442/542b: Artificial ntelligence Prof. Olga Veksler Lecture 16: Computer Vision Motion Slides are from Steve Seitz (UW), David Jacobs (UMD) Outline Motion Estimation Motion Field Optical Flow Field Methods

More information

Image Processing

Image Processing Image Processing 159.731 Canny Edge Detection Report Syed Irfanullah, Azeezullah 00297844 Danh Anh Huynh 02136047 1 Canny Edge Detection INTRODUCTION Edges Edges characterize boundaries and are therefore

More information

Def De orma f tion orma Disney/Pixar

Def De orma f tion orma Disney/Pixar Deformation Disney/Pixar Deformation 2 Motivation Easy modeling generate new shapes by deforming existing ones 3 Motivation Easy modeling generate new shapes by deforming existing ones 4 Motivation Character

More information

Laplacian Meshes. COS 526 Fall 2016 Slides from Olga Sorkine and Yaron Lipman

Laplacian Meshes. COS 526 Fall 2016 Slides from Olga Sorkine and Yaron Lipman Laplacian Meshes COS 526 Fall 2016 Slides from Olga Sorkine and Yaron Lipman Outline Differential surface representation Ideas and applications Compact shape representation Mesh editing and manipulation

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

Image Warping and Mosacing

Image Warping and Mosacing Image Warping and Mosacing 15-463: Rendering and Image Processing Alexei Efros with a lot of slides stolen from Steve Seitz and Rick Szeliski Today Mosacs Image Warping Homographies Programming Assignment

More information

Video 9.1 Jianbo Shi. Property of Penn Engineering, Jianbo Shi

Video 9.1 Jianbo Shi. Property of Penn Engineering, Jianbo Shi Video 9.1 Jianbo Shi 1 Exmples of resizing 2 820 546 3 3 420 546 3 (a) (b) (c) Guess We use crop, scaling and carving for resizing the given image Guess which one is for carving? 4 5 6 Guess which one

More information

Nonhomogeneous Scaling Optimization for Realtime Image Resizing

Nonhomogeneous Scaling Optimization for Realtime Image Resizing Noname manuscript No. (will be inserted by the editor) Nonhomogeneous Scaling Optimization for Realtime Image Resizing Yong Jin Ligang Liu Qingbiao Wu Received: date / Accepted: date Abstract We present

More information

Geometric modeling 1

Geometric modeling 1 Geometric Modeling 1 Look around the room. To make a 3D model of a room requires modeling every single object you can see. Leaving out smaller objects (clutter) makes the room seem sterile and unrealistic

More information

What will we learn? Geometric Operations. Mapping and Affine Transformations. Chapter 7 Geometric Operations

What will we learn? Geometric Operations. Mapping and Affine Transformations. Chapter 7 Geometric Operations What will we learn? Lecture Slides ME 4060 Machine Vision and Vision-based Control Chapter 7 Geometric Operations What do geometric operations do to an image and what are they used for? What are the techniques

More information

CoE4TN4 Image Processing

CoE4TN4 Image Processing CoE4TN4 Image Processing Chapter 11 Image Representation & Description Image Representation & Description After an image is segmented into regions, the regions are represented and described in a form suitable

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

Jump Stitch Metadata & Depth Maps Version 1.1

Jump Stitch Metadata & Depth Maps Version 1.1 Jump Stitch Metadata & Depth Maps Version 1.1 jump-help@google.com Contents 1. Introduction 1 2. Stitch Metadata File Format 2 3. Coverage Near the Poles 4 4. Coordinate Systems 6 5. Camera Model 6 6.

More information

CSE528 Computer Graphics: Theory, Algorithms, and Applications

CSE528 Computer Graphics: Theory, Algorithms, and Applications CSE528 Computer Graphics: Theory, Algorithms, and Applications Hong Qin Stony Brook University (SUNY at Stony Brook) Stony Brook, New York 11794-2424 Tel: (631)632-845; Fax: (631)632-8334 qin@cs.stonybrook.edu

More information

Dynamic Programming 1

Dynamic Programming 1 Dynamic Programming 1 Jie Wang University of Massachusetts Lowell Department of Computer Science 1 I thank Prof. Zachary Kissel of Merrimack College for sharing his lecture notes with me; some of the examples

More information

Skybox. Ruoqi He & Chia-Man Hung. February 26, 2016

Skybox. Ruoqi He & Chia-Man Hung. February 26, 2016 Skybox Ruoqi He & Chia-Man Hung February 26, 206 Introduction In this project, we present a method to construct a skybox from a series of photos we took ourselves. It is a graphical procedure of creating

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 14 130307 http://www.ee.unlv.edu/~b1morris/ecg795/ 2 Outline Review Stereo Dense Motion Estimation Translational

More information

Feature descriptors and matching

Feature descriptors and matching Feature descriptors and matching Detections at multiple scales Invariance of MOPS Intensity Scale Rotation Color and Lighting Out-of-plane rotation Out-of-plane rotation Better representation than color:

More information

Anno accademico 2006/2007. Davide Migliore

Anno accademico 2006/2007. Davide Migliore Robotica Anno accademico 6/7 Davide Migliore migliore@elet.polimi.it Today What is a feature? Some useful information The world of features: Detectors Edges detection Corners/Points detection Descriptors?!?!?

More information

Image Composition. COS 526 Princeton University

Image Composition. COS 526 Princeton University Image Composition COS 526 Princeton University Modeled after lecture by Alexei Efros. Slides by Efros, Durand, Freeman, Hays, Fergus, Lazebnik, Agarwala, Shamir, and Perez. Image Composition Jurassic Park

More information

Subdivision. Outline. Key Questions. Subdivision Surfaces. Advanced Computer Graphics (Spring 2013) Video: Geri s Game (outside link)

Subdivision. Outline. Key Questions. Subdivision Surfaces. Advanced Computer Graphics (Spring 2013) Video: Geri s Game (outside link) Advanced Computer Graphics (Spring 03) CS 83, Lecture 7: Subdivision Ravi Ramamoorthi http://inst.eecs.berkeley.edu/~cs83/sp3 Slides courtesy of Szymon Rusinkiewicz, James O Brien with material from Denis

More information

IEEE Consumer Electronics Society Calibrating a VR Camera. Adam Rowell CTO, Lucid VR

IEEE Consumer Electronics Society Calibrating a VR Camera. Adam Rowell CTO, Lucid VR IEEE Consumer Electronics Society Calibrating a VR Camera Adam Rowell CTO, Lucid VR adam@lucidcam.com Virtual Reality Cameras Lucid VR Camera How Does it Work? Lucid Software Technology Recording: Synchronization

More information

Spatially-Varying Image Warps for Scene Alignment

Spatially-Varying Image Warps for Scene Alignment Spatially-Varying Image Warps for Scene Alignment Che-Han Chang Graduate Institute of Networking and Multimedia National Taiwan University Taipei, Taiwan 106 Email: frank@cmlab.csie.ntu.edu.tw Chiu-Ju

More information

Free-Form Deformation and Other Deformation Techniques

Free-Form Deformation and Other Deformation Techniques Free-Form Deformation and Other Deformation Techniques Deformation Deformation Basic Definition Deformation: A transformation/mapping of the positions of every particle in the original object to those

More information

CS223b Midterm Exam, Computer Vision. Monday February 25th, Winter 2008, Prof. Jana Kosecka

CS223b Midterm Exam, Computer Vision. Monday February 25th, Winter 2008, Prof. Jana Kosecka CS223b Midterm Exam, Computer Vision Monday February 25th, Winter 2008, Prof. Jana Kosecka Your name email This exam is 8 pages long including cover page. Make sure your exam is not missing any pages.

More information

Image warping and stitching

Image warping and stitching Image warping and stitching Thurs Oct 15 Last time Feature-based alignment 2D transformations Affine fit RANSAC 1 Robust feature-based alignment Extract features Compute putative matches Loop: Hypothesize

More information

CS 523: Computer Graphics, Spring Shape Modeling. Skeletal deformation. Andrew Nealen, Rutgers, /12/2011 1

CS 523: Computer Graphics, Spring Shape Modeling. Skeletal deformation. Andrew Nealen, Rutgers, /12/2011 1 CS 523: Computer Graphics, Spring 2011 Shape Modeling Skeletal deformation 4/12/2011 1 Believable character animation Computers games and movies Skeleton: intuitive, low-dimensional subspace Clip courtesy

More information

Seam Carving for Content-Aware Image Resizing

Seam Carving for Content-Aware Image Resizing Seam Carving for Content-Aware Image Resizing Shai Avidan Mitsubishi Electric Research Labs Ariel Shamir The Interdisciplinary Center & MERL Figure 1: A seam is a connected path of low energy pixels in

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

Computer Vision. Recap: Smoothing with a Gaussian. Recap: Effect of σ on derivatives. Computer Science Tripos Part II. Dr Christopher Town

Computer Vision. Recap: Smoothing with a Gaussian. Recap: Effect of σ on derivatives. Computer Science Tripos Part II. Dr Christopher Town Recap: Smoothing with a Gaussian Computer Vision Computer Science Tripos Part II Dr Christopher Town Recall: parameter σ is the scale / width / spread of the Gaussian kernel, and controls the amount of

More information

CSE528 Computer Graphics: Theory, Algorithms, and Applications

CSE528 Computer Graphics: Theory, Algorithms, and Applications CSE528 Computer Graphics: Theory, Algorithms, and Applications Hong Qin State University of New York at Stony Brook (Stony Brook University) Stony Brook, New York 11794--4400 Tel: (631)632-8450; Fax: (631)632-8334

More information

I. INTRODUCTION CONTENT-AWARE retargeting has drawn increasing

I. INTRODUCTION CONTENT-AWARE retargeting has drawn increasing IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, VOL. 26, NO. 5, MAY 2016 801 Consistent Volumetric Warping Using Floating Boundaries for Stereoscopic Video Retargeting Shih-Syun Lin, Chao-Hung

More information

Real-Time Warps for Improved Wide-Angle Viewing

Real-Time Warps for Improved Wide-Angle Viewing Real-Time Warps for Improved Wide-Angle Viewing Zicheng Liu zliu@microsoft.com November 2002 Technical Report MSR-TR-2002-110 Michael Cohen mcohen@microsoft.com Microsoft Research Microsoft Corporation

More information

Biometrics Technology: Image Processing & Pattern Recognition (by Dr. Dickson Tong)

Biometrics Technology: Image Processing & Pattern Recognition (by Dr. Dickson Tong) Biometrics Technology: Image Processing & Pattern Recognition (by Dr. Dickson Tong) References: [1] http://homepages.inf.ed.ac.uk/rbf/hipr2/index.htm [2] http://www.cs.wisc.edu/~dyer/cs540/notes/vision.html

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

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

Today s lecture. Image Alignment and Stitching. Readings. Motion models

Today s lecture. Image Alignment and Stitching. Readings. Motion models Today s lecture Image Alignment and Stitching Computer Vision CSE576, Spring 2005 Richard Szeliski Image alignment and stitching motion models cylindrical and spherical warping point-based alignment global

More information

Graphic Design & Digital Photography. Photoshop Basics: Working With Selection.

Graphic Design & Digital Photography. Photoshop Basics: Working With Selection. 1 Graphic Design & Digital Photography Photoshop Basics: Working With Selection. What You ll Learn: Make specific areas of an image active using selection tools, reposition a selection marquee, move and

More information

Introduction to Computer Graphics. Image Processing (1) June 8, 2017 Kenshi Takayama

Introduction to Computer Graphics. Image Processing (1) June 8, 2017 Kenshi Takayama Introduction to Computer Graphics Image Processing (1) June 8, 2017 Kenshi Takayama Today s topics Edge-aware image processing Gradient-domain image processing 2 Image smoothing using Gaussian Filter Smoothness

More information

Image Warping. Srikumar Ramalingam School of Computing University of Utah. [Slides borrowed from Ross Whitaker] 1

Image Warping. Srikumar Ramalingam School of Computing University of Utah. [Slides borrowed from Ross Whitaker] 1 Image Warping Srikumar Ramalingam School of Computing University of Utah [Slides borrowed from Ross Whitaker] 1 Geom Trans: Distortion From Optics Barrel Distortion Pincushion Distortion Straight lines

More information

CSE328 Fundamentals of Computer Graphics

CSE328 Fundamentals of Computer Graphics CSE328 Fundamentals of Computer Graphics Hong Qin State University of New York at Stony Brook (Stony Brook University) Stony Brook, New York 794--44 Tel: (63)632-845; Fax: (63)632-8334 qin@cs.sunysb.edu

More information

PatchMatch: A Randomized Correspondence Algorithm for Structural Image Editing

PatchMatch: A Randomized Correspondence Algorithm for Structural Image Editing PatchMatch: A Randomized Correspondence Algorithm for Structural Image Editing Barnes et al. In SIGGRAPH 2009 발표이성호 2009 년 12 월 3 일 Introduction Image retargeting Resized to a new aspect ratio [Rubinstein

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

CSE 554 Lecture 6: Fairing and Simplification

CSE 554 Lecture 6: Fairing and Simplification CSE 554 Lecture 6: Fairing and Simplification Fall 2012 CSE554 Fairing and simplification Slide 1 Review Iso-contours in grayscale images and volumes Piece-wise linear representations Polylines (2D) and

More information

Images from 3D Creative Magazine. 3D Modelling Systems

Images from 3D Creative Magazine. 3D Modelling Systems Images from 3D Creative Magazine 3D Modelling Systems Contents Reference & Accuracy 3D Primitives Transforms Move (Translate) Rotate Scale Mirror Align 3D Booleans Deforms Bend Taper Skew Twist Squash

More information

Ptex: Per-face Texture Mapping for Production Rendering

Ptex: Per-face Texture Mapping for Production Rendering EGSR 2008 Ptex: Per-face Texture Mapping for Production Rendering Brent Burley and Dylan Lacewell Walt Disney Animation Studios (See attached slide notes for details) Texture Mapping at Disney Chicken

More information

Edge and local feature detection - 2. Importance of edge detection in computer vision

Edge and local feature detection - 2. Importance of edge detection in computer vision Edge and local feature detection Gradient based edge detection Edge detection by function fitting Second derivative edge detectors Edge linking and the construction of the chain graph Edge and local feature

More information

03 Vector Graphics. Multimedia Systems. 2D and 3D Graphics, Transformations

03 Vector Graphics. Multimedia Systems. 2D and 3D Graphics, Transformations Multimedia Systems 03 Vector Graphics 2D and 3D Graphics, Transformations Imran Ihsan Assistant Professor, Department of Computer Science Air University, Islamabad, Pakistan www.imranihsan.com Lectures

More information

TRANSCODING CACHE FOR SMART PHONES

TRANSCODING CACHE FOR SMART PHONES TRANSCODING CACHE FOR SMART PHONES Pitiphong Phongpattranont Department of Computer Engineering Chulalongkorn University Bangkok, Thailand Abstract In this paper, we present Transcoding Cache (TC), a new

More information

Image stitching. Digital Visual Effects Yung-Yu Chuang. with slides by Richard Szeliski, Steve Seitz, Matthew Brown and Vaclav Hlavac

Image stitching. Digital Visual Effects Yung-Yu Chuang. with slides by Richard Szeliski, Steve Seitz, Matthew Brown and Vaclav Hlavac Image stitching Digital Visual Effects Yung-Yu Chuang with slides by Richard Szeliski, Steve Seitz, Matthew Brown and Vaclav Hlavac Image stitching Stitching = alignment + blending geometrical registration

More information

Today. Motivation. Motivation. Image gradient. Image gradient. Computational Photography

Today. Motivation. Motivation. Image gradient. Image gradient. Computational Photography Computational Photography Matthias Zwicker University of Bern Fall 009 Today Gradient domain image manipulation Introduction Gradient cut & paste Tone mapping Color-to-gray conversion Motivation Cut &

More information