| Tools for Intelligent Computer Graphics | p. 1 |
| Introduction | p. 1 |
| Elements of Artificial Intelligence for Computer Graphics | p. 3 |
| Problem resolution | p. 5 |
| General Considerations | p. 5 |
| Strategy games | p. 5 |
| Constraint satisfaction | p. 6 |
| The Resolution Process | p. 7 |
| Constraint Logic Programming on Finite Domains -CLP(FD) | p. 8 |
| Expert Systems | p. 9 |
| Rules and inference engine of expert systems | p. 10 |
| Main strategies for applying rules | p. 11 |
| Machine-learning | p. 11 |
| Neural networks | p. 12 |
| Genetic algorithms | p. 14 |
| Artificial Intelligence and Computer Graphics | p. 15 |
| What is viewpoint complexity in Computer Graphics? | p. 17 |
| How to compute visual complexity? | p. 18 |
| Accurate visual complexity estimation | p. 19 |
| Fast approximate estimation of visual complexity | p. 22 |
| Conclusion | p. 23 |
| References | p. 24 |
| Intelligent scene modeling | p. 27 |
| Introduction | p. 27 |
| Declarative scene modeling | p. 28 |
| The PolyFormes Declarative Scene Modeler | p. 29 |
| The MultiFormes Declarative Scene Modeler | p. 29 |
| The DE2MONS Declarative Scene Modeler | p. 30 |
| The VoluFormes Declarative Scene Modeler | p. 30 |
| The description phase in declarative scene modeling | p. 31 |
| Set of rules and facts | p. 31 |
| Set of arithmetic or geometric constraints | p. 32 |
| The generation phase in declarative scene modeling | p. 34 |
| Set of rules and facts | p. 34 |
| Set of arithmetic or geometric constraints | p. 41 |
| Further generation improvements | p. 49 |
| Neural network-based machine-learning | p. 50 |
| Genetic algorithm-based machine-learning | p. 56 |
| The scene understanding phase in declarative scene modeling | p. 59 |
| Conclusion | p. 61 |
| References | p. 62 |
| Scene understanding | p. 65 |
| Introduction | p. 65 |
| Static scene understanding | p. 66 |
| Non degenerated views | p. 67 |
| Direct approximate viewpoint calculation | p. 68 |
| Iterative viewpoint calculation | p. 70 |
| The viewpoint quality criterion | p. 74 |
| Fast viewpoint quality calculation | p. 75 |
| Information theory-based viewpoint calculation | p. 76 |
| Total curvature-based viewpoint calculation | p. 78 |
| Mesh Saliency-based viewpoint calculation | p. 81 |
| Object understanding-based viewpoint calculation | p. 82 |
| A priori viewpoint calculation | p. 85 |
| Processing of form properties | p. 88 |
| Processing of placement properties | p. 89 |
| Conclusion | p. 92 |
| References | p. 93 |
| Virtual World Exploration | p. 95 |
| Introduction | p. 95 |
| Global incremental online exploration | p. 97 |
| A heuristic method to guide the movement of a camera | p. 99 |
| Fast computation of good view directions | p. 101 |
| Camera movement heuristics | p. 103 |
| Viewpoint entropy-based online exploration | p. 106 |
| Goal-based global online exploration | p. 108 |
| Main principles of goal-based exploration | p. 108 |
| Implementation of exploration techniques and results | p. 1ll |
| Discussion | p. 115 |
| Local incremental online exploration | p. 117 |
| Preprocessing: analysis of the scene | p. 118 |
| Determining the trajectory of the camera | p. 120 |
| Processing of a point of passage | p. 122 |
| Discussion | p. 122 |
| Minimal viewpoint set-based global offline Exploration | p. 124 |
| Computing an initial set of points of view | p. 124 |
| Total curvature-based global offline exploration | p. 139 |
| Offline construction of a visibility graph | p. 139 |
| Incremental computation of the camera trajectory | p. 140 |
| Further exploration of a virtual world | p. 142 |
| Some results | p. 142 |
| Local offline exploration | p. 144 |
| Construction of the visibility graph | p. 144 |
| Computation of pertinent views | p. 145 |
| Computation of camera trajectory | p. 146 |
| Improvements | p. 148 |
| Conclusion | p. 151 |
| References | p. 152 |
| Improvements and applications | p. 155 |
| Introduction | p. 155 |
| Scene understanding and lighting | p. 157 |
| Absolute light source placement | p. 158 |
| Taking into account light source position | p. 159 |
| A naive first approach | p. 160 |
| Refining the method | p. 162 |
| Indirect lighting | p. 163 |
| Automatic computation of the best viewpoint | p. 164 |
| Automatic scene exploration | p. 164 |
| First results | p. 165 |
| Discussion | p. 168 |
| Viewpoint complexity and image-based modeling | p. 169 |
| Computing a minimal set of viewpoints - First method | p. 169 |
| Computing a minimal set of viewpoints - Second method | p. 170 |
| Evaluating camera positions | p. 171 |
| Computing a minimal set of camera positions | p. 171 |
| Some results | p. 172 |
| Viewpoint complexity and ray-tracing | p. 172 |
| Viewpoint complexity and molecular visualization | p. 173 |
| Conclusion | p. 175 |
| References | p. 176 |
| Viewpoint Complexity in Radiosity | p. 179 |
| Introduction | p. 179 |
| Radiosity and form factors | p. 180 |
| The Hemi-cube Method for Computing Form Factors | p. 181 |
| The hemi-cube selective refinement technique | p. 182 |
| Selective Refinement | p. 182 |
| Selective Refinement for Computing Form Factors | p. 183 |
| Hemisphere subdivision techniques | p. 187 |
| Progressive refinement and Monte Carlo-based techniques | p. 187 |
| Progressive Radiosity | p. 187 |
| Monte-Carlo Radiosity | p. 188 |
| Monte-Carlo Progressive Radiosity | p. 188 |
| The first hemisphere subdivision technique | p. 189 |
| Evaluation of the first hemisphere subdivision method | p. 192 |
| A new approach of hemisphere subdivision | p. 194 |
| Preprocessing | p. 194 |
| Radiosity computation | p. 196 |
| Discussion and results | p. 198 |
| Conclusion | p. 201 |
| Pyramidal subdivision | p. 202 |
| Pyramidal hemisphere subdivision | p. 202 |
| Adaptive Pyramidal Subdivision | p. 203 |
| Regular Pyramidal Subdivision | p. 205 |
| Number of Objects Contained Into a Pyramid | p. 207 |
| Discussion and Results | p. 209 |
| How to improve viewpoint complexity estimation | p. 211 |
| More accurate Monte Carlo radiosity | p. 212 |
| Subdivision depending on the neighboring regions | p. 213 |
| Preprocessing | p. 213 |
| Radiosity computation | p. 214 |
| Independent processing of regions | p. 214 |
| Preprocessing | p. 215 |
| Radiosity computation | p. 216 |
| Discussion | p. 216 |
| Conclusion | p. 216 |
| References | p. 219 |
| Scene understanding and human intelligence | p. 221 |
| Introduction | p. 221 |
| Main techniques for scene understanding | p. 223 |
| Best view computing for virtual worlds | p. 223 |
| Apparent contour extraction techniques | p. 226 |
| Image space algorithms | p. 227 |
| Hybrid algorithms | p. 227 |
| Object space algorithms | p. 227 |
| Understanding visually complex scenes | p. 230 |
| The selective refinement part | p. 231 |
| The code direction part | p. 232 |
| First results | p. 234 |
| Discussion | p. 237 |
| Understanding scenes with hidden details | p. 238 |
| Using different rendering modes | p. 239 |
| Creating holes on the external surfaces of the scene | p. 239 |
| Using a preprocessing step | p. 240 |
| Suppression of useless polygons during rendering | p. 240 |
| Some results | p. 240 |
| Discussion | p. 244 |
| References | p. 245 |
| Table of Contents provided by Ingram. All Rights Reserved. |