texture
play

Texture CS 419 Slides by Ali Farhadi What is a Texture? Texture - PowerPoint PPT Presentation

Dec 27, 2023 •297 likes •1.1k views

Texture CS 419 Slides by Ali Farhadi What is a Texture? Texture Spectrum Steven Li, James Hays, Chenyu Wu, Vivek Kwatra, and Yanxi Liu, CVPR 06 Texture scandals!! Two crucial algorithmic points Nearest neighbors again and again

  1. Texture CS 419 Slides by Ali Farhadi

  2. What is a Texture?

  3. Texture Spectrum Steven Li, James Hays, Chenyu Wu, Vivek Kwatra, and Yanxi Liu, CVPR 06

  4. Texture scandals!!

  6. Two crucial algorithmic points • Nearest neighbors • again and again and again • Dynamic programming • likely new; we’ll use this again, too

  7. Texture Synthesis Efros & Leung ICCV99

  8. How to paint this pixel? ? p Input texture Efros & Leung ICCV99

  9. Ask Neighbors p p • What is the conditional probability distribution of p, given it’s neighbors? Efros & Leung ICCV99

  10. Input image • Don’t bother to model the distribution • It’s already there, in the image Efros & Leung ICCV99

  11. Efros & Leung Algorithm non-parametric sampling p Input image Synthesizing a pixel Efros & Leung ICCV99

  12. Concerns • Distance metric • Neighborhood size • Order to paint

  13. Distance metric • Normalized sum of squared distances • Not all the neighbors worth the same • Gaussian mask • Preserve the local structure • Pick among reasonably similar neighborhoods

  14. Neighborhood size input Efros & Leung ICCV99

  15. Varying Window Size Increasing window size Efros & Leung ICCV99

  16. The Order matters

  17. Some Results Efros & Leung ICCV99

  18. More Results Efros & Leung ICCV99

  19. More Results french canvas rafia weave Efros & Leung ICCV99

  20. wood granite More Results Efros & Leung ICCV99

  21. white bread brick wall More Results Efros & Leung ICCV99

  22. Growing Regions Hole Filling Efros & Leung ICCV99

  23. Hole Filling Efros & Leung ICCV99

  24. Extrapolation Efros & Leung ICCV99

  25. Failure Cases Growing garbage Verbatim copying Efros & Leung ICCV99

  26. Pros and Cons • Very simple • Easy to implement • Promising results • Very sloooooooowwwwwww • Idea: • Patches instead of pixels

  27. Patch based non-parametric sampling B Synthesizing a block Input image • Observation • neighbouring pixels are highly correlated • Idea: • unit of synthesis = block Efros & Freeman SIGGRAPH01

  28. block Input texture B1 B2 B1 B1 B2 B2 Random placement Neighboring blocks Minimal error of blocks constrained by overlap boundary cut Efros & Freeman SIGGRAPH01

  29. Minimal error boundary overlapping blocks vertical boundary 2 _ = overlap error min. error boundary Efros & Freeman SIGGRAPH01

  30. Dynamic Programming S T

  31. Dynamic Programming S T

  32. B1 B2 B1 B1 B2 B2 Random placement Neighboring blocks Minimal error of blocks constrained by overlap boundary cut Efros & Freeman SIGGRAPH01

  33. More Results Efros & Freeman SIGGRAPH01

  34. More Results Efros & Freeman SIGGRAPH01

  35. Efros & Freeman SIGGRAPH01

  36. Efros & Freeman SIGGRAPH01

  37. Efros & Freeman SIGGRAPH01

  38. Efros & Freeman SIGGRAPH01

  39. Failures Efros & Freeman SIGGRAPH01

  40. Texture Transfer • Take the texture from on object and paint it on another object = + Decomposing shape and texture Very challenging Walk around Add some constraint to the search Efros & Freeman SIGGRAPH01

  41. Destination Source Texture Destination Map Source Map

  43. Texture Transfer + = Efros & Freeman SIGGRAPH01

  44. + = Efros & Freeman SIGGRAPH01

  45. Efros & Freeman SIGGRAPH01

  46. parmesan + = rice + = Efros & Freeman SIGGRAPH01

  47. Image Analogies ? Hertzman, Jacobs, Oliver, Curless, and Salesin, SIGGRAPH01

  48. Image Analogies Hertzman, Jacobs, Oliver, Curless, and Salesin, SIGGRAPH01

  49. Image Analogies Hertzman, Jacobs, Oliver, Curless, and Salesin, SIGGRAPH01

  50. Image Analogies Hertzman, Jacobs, Oliver, Curless, and Salesin, SIGGRAPH01

  51. Training Hertzman, Jacobs, Oliver, Curless, and Salesin, SIGGRAPH01

  52. :: : B B’ Hertzman, Jacobs, Oliver, Curless, and Salesin, SIGGRAPH01

  53. Hertzman, Jacobs, Oliver, Curless, and Salesin, SIGGRAPH01

  54. :: : B B’ Hertzman, Jacobs, Oliver, Curless, and Salesin, SIGGRAPH01

  55. Hertzman, Jacobs, Oliver, Curless, and Salesin, SIGGRAPH01

  56. Learn to Blur Hertzman, Jacobs, Oliver, Curless, and Salesin, SIGGRAPH01

  57. Texture by Numbers Hertzman, Jacobs, Oliver, Curless, and Salesin, SIGGRAPH01

  58. Colorization Hertzman, Jacobs, Oliver, Curless, and Salesin, SIGGRAPH01

  59. Super-resolution A A’ Hertzman, Jacobs, Oliver, Curless, and Salesin, SIGGRAPH01

  60. Super-resolution (result!) B’ B Hertzman, Jacobs, Oliver, Curless, and Salesin, SIGGRAPH01

  61. Training images Hertzman, Jacobs, Oliver, Curless, and Salesin, SIGGRAPH01

  62. Hertzman, Jacobs, Oliver, Curless, and Salesin, SIGGRAPH01

  63. Inpainting Criminisi et.al. CVPR03

  64. Order of inpainting matters Criminisi et al, 04

  65. Choosing the order Criminisi et al 03

  66. Constraining the match region • We don’t have to look for matches in the whole image • idea: allow user to “paint” good sources of matches on top of the image

  67. Nearest Neighbor search The core of most of the patch based methods Very slow Smarter neighborhood search Barnes et.al. SIGGRAPH09

  68. Inpainting Barnes et.al. SIGGRAPH09

  69. Applications Barnes et.al. SIGGRAPH09

  70. Retargeting • Make an image bigger or smaller in one direction • eg change aspect ratio • Traditional • cut off pixels • difficulty: lousy results • Strategy • cut out a curve of pixels that “doesn’t matter much” • low energy at pixels • many energy functions, eg

  71. Finding a seam=DP Avidan, Shamir, SIGGRAPH07

  72. • Different energies give different results • e1 = abs gradient (as above) • ehog = (look for gradients in patch) • eentropy = (entropy of patch) • eseg = (segment image, e1 in segments, 0 on boundaries)

  73. Retargeting Seam removal Scaling Cropping Avidan, Shamir, SIGGRAPH07

  74. Retargeting Avidan, Shamir, SIGGRAPH07

  75. Avidan, Shamir, SIGGRAPH07

  76. Can use constraints in retargeting Barnes et.al. SIGGRAPH09

  77. Constrained retargeting Barnes et.al. SIGGRAPH09

  78. Local scale editing Barnes et.al. SIGGRAPH09

  79. reshuffling Barnes et.al. SIGGRAPH09

  80. Barnes et.al. SIGGRAPH09

Download Presentation
Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend

Shape from Texture Texture Discrimination 1 Texture Texture Synthesis Goal of texture

Shape from Texture Texture Discrimination 1 Texture Texture Synthesis Goal of texture

Texture Modeling Texture What is texture? Easy to recognize, hard to define Deterministic/regular textures (thing-like) Stochastic textures (stuff-like) Tasks What is texture? Discrimination / Segmentation An

312 views • 29 slides
C P S C 314 WHY IS TEXTURE IMPORTANT? TEXTURE MAPPING TEXTURE MAPPING TEXTURE MAPPING real

C P S C 314 WHY IS TEXTURE IMPORTANT? TEXTURE MAPPING TEXTURE MAPPING TEXTURE MAPPING real

C P S C 314 WHY IS TEXTURE IMPORTANT? TEXTURE MAPPING TEXTURE MAPPING TEXTURE MAPPING real life objects have hide geometric simplicity nonuniform colors, normals images convey illusion of geometry to generate realistic objects,

448 views • 3 slides
Topic 11: Texture Mapping Motivation Sources of texture Texture coordinates

Topic 11: Texture Mapping Motivation Sources of texture Texture coordinates

11/13/2017 Topic 11: Texture Mapping Motivation Sources of texture Texture coordinates Bump mapping, mipmapping & env mapping Texture sources: Photographs Texture sources: Procedural Texture sources: Solid textures

492 views • 11 slides
1 L Feb-20-04 SMD159, Texture in OpenGL Overview OpenGL texture functions and options 2 L

1 L Feb-20-04 SMD159, Texture in OpenGL Overview OpenGL texture functions and options 2 L

INSTITUTIONEN FR SYSTEMTEKNIK LULE TEKNISKA UNIVERSITET Texture in OpenGL David Carr Fundamentals of Computer Graphics Spring 2004 Based on Slides by E. Angel 1 L Feb-20-04 SMD159, Texture in OpenGL Overview OpenGL texture

463 views • 9 slides
Texture Mapping Texture (images) lecture 16 Texture mapping Aliasing (and anti-aliasing)

Texture Mapping Texture (images) lecture 16 Texture mapping Aliasing (and anti-aliasing)

Texture Mapping Texture (images) lecture 16 Texture mapping Aliasing (and anti-aliasing) Adding texture improves realism. Q: Why do we need texture mapping ? A: Because objects look fake and boring without it. recall mapping for

176 views • 6 slides
lecture 16 Texture mapping Aliasing (and anti-aliasing) Texture (images) Texture Mapping Q:

lecture 16 Texture mapping Aliasing (and anti-aliasing) Texture (images) Texture Mapping Q:

lecture 16 Texture mapping Aliasing (and anti-aliasing) Texture (images) Texture Mapping Q: Why do we need texture mapping ? A: Because objects look fake and boring without it. Adding texture improves realism. recall mapping for

513 views • 48 slides
Page 1 1 Texture Pipeline Texture Pipeline Compute Use projector Use corresponder t eye

Page 1 1 Texture Pipeline Texture Pipeline Compute Use projector Use corresponder t eye

University of British Columbia Correction & Review: Surface Texture CPSC 314 Computer Graphics define texture pattern over (s,t) domain Jan-Apr 2005 image 2D array of texels Tamara Munzner assign (s,t) coordinates to

352 views • 6 slides
Texture Synthesis Given a texture, create more CS176: Texture Synthesis All examples from Wei

Texture Synthesis Given a texture, create more CS176: Texture Synthesis All examples from Wei

Texture Synthesis Given a texture, create more CS176: Texture Synthesis All examples from Wei & Levoy CS 176 Winter 2011 CS 176 Winter 2011 1 2 Texture Synthesis Texture Synthesis Dont expect too much And amazing successes All

347 views • 3 slides
Texture Advection 6-1 Ronald Peikert SciVis 2007 - Texture Advection Texture advection

Texture Advection 6-1 Ronald Peikert SciVis 2007 - Texture Advection Texture advection

Texture Advection 6-1 Ronald Peikert SciVis 2007 - Texture Advection Texture advection Motivation: dense visualization of vector fields, no seed points needed. Methods for static fields: LIC LIC - Line integral convolution

520 views • 27 slides
Topic 12: Texture Mapping Motivation Sources of texture Texture coordinates Bump

Topic 12: Texture Mapping Motivation Sources of texture Texture coordinates Bump

Topic 12: Texture Mapping Motivation Sources of texture Texture coordinates Bump mapping, mip-mapping & env mapping Texture sources: Photographs Texture sources: Procedural Texture sources: Solid textures Texture sources:

1.03k views • 54 slides
Texture Texture Discrimination What is texture? Easy to recognize, hard to define

Texture Texture Discrimination What is texture? Easy to recognize, hard to define

Texture Texture Discrimination What is texture? Easy to recognize, hard to define Deterministic textures (thing-like) Stochastic textures (stuff-like) Tasks Discrimination / Segmentation Classification

192 views • 17 slides
6.1 Texture Mapping Hao Li http://cs420.hao-li.com 1 Outline Introduction Texture

6.1 Texture Mapping Hao Li http://cs420.hao-li.com 1 Outline Introduction Texture

Fall 2018 CSCI 420: Computer Graphics 6.1 Texture Mapping Hao Li http://cs420.hao-li.com 1 Outline Introduction Texture mapping in OpenGL Filtering and Mipmaps Example Non-color texture maps 2 How Do You Add Detail to a

762 views • 52 slides
Outline Texture Mapping Modeling surface details with images. Roger Crawfis Texture

Outline Texture Mapping Modeling surface details with images. Roger Crawfis Texture

Outline Texture Mapping Modeling surface details with images. Roger Crawfis Texture parameterization Ohio State University Texture evaluation Anti-aliasing and textures. Texture Mapping Texture Mapping Why use textures?

889 views • 54 slides
Outline Texture Mapping Modeling surface details with images. Roger Crawfis Texture

Outline Texture Mapping Modeling surface details with images. Roger Crawfis Texture

Outline Texture Mapping Modeling surface details with images. Roger Crawfis Texture parameterization Ohio State University Texture evaluation Anti-aliasing and textures. Texture Mapping Texture Mapping Why use textures?

246 views • 20 slides
+ + = = geometry geometry image image texture map texture map Q: How do we decide

+ + = = geometry geometry image image texture map texture map Q: How do we decide

So Far Texture Mapping o We have assumed that we know: o Texture effects can be added o The point to give more realistic looking o The surface normal surface appearance o The viewer location (or direction) o The light location (or

403 views • 9 slides
Texture S ynthesis Daniel Cohen-Or + = + = = The Goal of Texture Synthesis input image

Texture S ynthesis Daniel Cohen-Or + = + = = The Goal of Texture Synthesis input image

Texture S ynthesis Daniel Cohen-Or + = + = = The Goal of Texture Synthesis input image SYNTHESIS True (infinite) texture generated image Given a finite sample (large enough) of some texture, the goal is to synthesize other samples

978 views • 68 slides
NMR Spectroscopy Dr. Joshua Osbourn Dept. of Chemistry, West Virginia University 1. Theory of

NMR Spectroscopy Dr. Joshua Osbourn Dept. of Chemistry, West Virginia University 1. Theory of

NMR Spectroscopy Dr. Joshua Osbourn Dept. of Chemistry, West Virginia University 1. Theory of NMR Spectroscopy 2. Spectrum Basics 3. Chemically Equivalent and Distinct Hydrogen 4. Chemical Shift 5. Integration (Peak Height) 6. Coupling

960 views • 40 slides
Convolutional Neural Nets CS447 Natural Language Processing (J. Hockenmaier)

Convolutional Neural Nets CS447 Natural Language Processing (J. Hockenmaier)

Lecture 8: Convolutional Neural Nets Convolutional Neural Nets CS447 Natural Language Processing (J. Hockenmaier) https://courses.grainger.illinois.edu/cs447/ 1 Convolutional Neural Nets (ConvNets, CNNs) [4 parameters, applied 3

615 views • 24 slides
A passion for precision Theodor W. Hnsch Max-Planck-Institute for Quantum Optics, Garching,

A passion for precision Theodor W. Hnsch Max-Planck-Institute for Quantum Optics, Garching,

Stockholm 2005 A passion for precision Theodor W. Hnsch Max-Planck-Institute for Quantum Optics, Garching, and Ludwig-Maximilians-University, Munich Stockholm, Dec. 8, 2005 University of Heidelberg, 1964 - 1970 Ali Javan Bill Bennett

1.04k views • 70 slides
An Introduction to IoT Penetration Testing @libertyunix www.kmco.com The Agenda n IoT Attack

An Introduction to IoT Penetration Testing @libertyunix www.kmco.com The Agenda n IoT Attack

An Introduction to IoT Penetration Testing @libertyunix www.kmco.com The Agenda n IoT Attack Surface l OWASP IoT Top 10 l -1 Ring in IoT n Wireless Topics in IoT n IoT Pen Testing Tools & Examples n Q&A 2 Getting Started in IoT

923 views • 52 slides
Hertzsprung-Russell 47 Tuc The Milky Way M74 M87 SNIa Hubble diagram 2dF COBE: CMB Rotation

Hertzsprung-Russell 47 Tuc The Milky Way M74 M87 SNIa Hubble diagram 2dF COBE: CMB Rotation

Hertzsprung-Russell 47 Tuc The Milky Way M74 M87 SNIa Hubble diagram 2dF COBE: CMB Rotation curves: DM? [Begeman 89]

211 views • 7 slides
Vehic icle-to to-Vehicle Message Content Pla lausibil ility Check through Low-Power Beaconing

Vehic icle-to to-Vehicle Message Content Pla lausibil ility Check through Low-Power Beaconing

Vehic icle-to to-Vehicle Message Content Pla lausibil ility Check through Low-Power Beaconing Taeho Kim , Hyogon Kim Department of Computer Science and Engineering Korea University VTC2017-Fall September 24-27 2017, Toronto, Canada Outline

461 views • 27 slides
Atoms The Basis of All Materials RPI - ERTH 2330 The Atom Neutron - neutral particle

Atoms The Basis of All Materials RPI - ERTH 2330 The Atom Neutron - neutral particle

Atoms The Basis of All Materials RPI - ERTH 2330 The Atom Neutron - neutral particle Proton - positively charged particle Electron - negatively charged particle E.B. Watson Our story begins with light Visible light part

484 views • 24 slides
CS 378: Autonomous Intelligent Robotics Instructor: Jivko Sinapov

CS 378: Autonomous Intelligent Robotics Instructor: Jivko Sinapov

CS 378: Autonomous Intelligent Robotics Instructor: Jivko Sinapov http://www.cs.utexas.edu/~jsinapov/teaching/cs378/ Audio Processing and Computational Perception of Natural Sound Why Sound? Why Sound? What actually happened: The robot

779 views • 65 slides

More recommend