+612 9045 4394
View Synthesis Using Stereo Vision : Lecture Notes in Computer Science - Daniel Scharstein

View Synthesis Using Stereo Vision

Lecture Notes in Computer Science

Paperback Published: 9th June 1999
ISBN: 9783540661597
Number Of Pages: 172

Share This Book:


or 4 easy payments of $33.88 with Learn more
Ships in 5 to 9 business days

Image-based rendering, as an area of overlap between computer graphics and computer vision, uses computer vision techniques to aid in sythesizing new views of scenes. Image-based rendering methods are having a substantial impact on the field of computer graphics, and also play an important role in the related field of multimedia systems, for applications such as teleconferencing, remote instruction and surgery, virtual reality and entertainment.
The book develops a novel way of formalizing the view synthesis problem under the full perspective model, yielding a clean, linear warping equation. It shows new techniques for dealing with visibility issues such as partial occlusion and "holes". Furthermore, the author thoroughly re-evaluates the requirements that view synthesis places on stereo algorithms and introduces two novel stereo algorithms specifically tailored to the application of view synthesis.

Introductionp. 1
The Problemp. 2
Applicationsp. 2
The Computer Graphics Approachp. 5
Avoiding the Modelp. 6
A Review of Stereo Visionp. 8
Camera Model and Image Formationp. 8
Stereo Geometryp. 10
The Correspondence Problemp. 13
The Epipolar Constraintp. 14
A Simple Stereo Geometryp. 16
Rectificationp. 17
Example: SSDp. 19
Contributions and Outlinep. 22
A Survey of Image-Based Rendering and Stereop. 23
Image-Based Renderingp. 23
View Synthesis Based on Stereop. 24
View Interpolationp. 27
Mosaics and Layered Representationsp. 29
Stereop. 32
A Framework for Stereop. 32
Preprocessingp. 33
Matching Costp. 33
Evidence Aggregationp. 34
Disparity Selectionp. 35
Sub-Pixel Disparity Computationp. 35
Diffusion-Based Techniquesp. 36
Other Techniquesp. 37
Promising Recent Approachesp. 37
Computer Vision Booksp. 38
View Synthesisp. 41
Geometryp. 42
Three-View Rectificationp. 42
The Linear Warping Equationp. 44
Computing the Rectifying Homographiesp. 45
Synthesizing a New Viewp. 47
Resolving Visibilityp. 47
Holes and Sampling Gapsp. 47
Combining Information from Both Imagesp. 48
Adjusting Intensitiesp. 49
Filling Holesp. 50
The View Synthesis Algorithmp. 51
Limitations of the Approachp. 52
Experimentsp. 53
Image-Based Scene Representationsp. 60
Summaryp. 61
Re-evaluating Stereop. 63
Traditional Applications of Stereop. 63
Automated Cartographyp. 64
Robot Navigationp. 64
3D Reconstructionp. 65
3D Recognitionp. 66
Visual Servoingp. 66
Full vs. Weak Calibrationp. 67
Comparison of Requirementsp. 68
Stereo for View Synthesisp. 68
Accuracyp. 69
Correct vs. Realistic Viewsp. 71
Areas of Uniform Intensitiesp. 72
Geometric Constraintsp. 73
Interpolated Viewsp. 75
Extrapolated Viewsp. 77
General Views and the Aperture Problemp. 79
Assigning Canonical Depth Interpretationsp. 80
Does Adding More Cameras Help?p. 80
Partial Occlusionp. 81
Summaryp. 85
Gradient-Based Stereop. 87
Similarity and Confidencep. 88
Displacement-Oriented Stereop. 89
The Evidence Measurep. 90
Comparing Two Gradient Vectorsp. 91
Comparing Gradient Fieldsp. 93
Computing Gradients of Discrete Imagesp. 94
Accumulating the Measurep. 96
Experimentsp. 97
Observing E¿ for Interesting Displacementsp. 98
Stereo: 1D Search Rangep. 98
General Motion: 2D Search Rangep. 105
Computing Disparity Maps for View Synthesisp. 105
Occlusion Boundariesp. 107
Detecting Partially Occluded Points and Uniform Regionsp. 109
Extrapolating the Disparitiesp. 109
Efficiencyp. 109
Discussion and Possible Extensionsp. 110
Summaryp. 111
Stereo Using Diffusionp. 113
Disparity Spacep. 114
The SSD Algorithm and Boundary Blurringp. 116
Aggregating Support by Diffusionp. 121
The Membrane Modelp. 122
Support Function for the Membrane Modelp. 123
Diffusion with Local Stoppingp. 125
A Bayesian Model of Stereo Matchingp. 127
The Prior Modelp. 127
The Measurement Modelp. 129
Explicit Local Distribution Modelp. 131
Experimentsp. 134
Discussion and Possible Extensionsp. 141
Summaryp. 144
Conclusionp. 145
Contributions in View Synthesisp. 145
Contributions in Stereop. 146
Extensions and Future Workp. 146
Bibliographyp. 149
Table of Contents provided by Publisher. All Rights Reserved.

ISBN: 9783540661597
ISBN-10: 354066159X
Series: Lecture Notes in Computer Science
Audience: General
Format: Paperback
Language: English
Number Of Pages: 172
Published: 9th June 1999
Publisher: Springer-Verlag Berlin and Heidelberg Gmbh & Co. Kg
Country of Publication: DE
Dimensions (cm): 23.39 x 15.6  x 1.02
Weight (kg): 0.27