## 3-D Shape Estimation and Image Restoration: Exploiting Defocus and Motion-BlurImages contain information about the spatial properties of the scene they depict. When coupled with suitable assumptions, images can be used to infer thr- dimensional information. For instance, if the scene contains objects made with homogeneous material, such as marble, variations in image intensity can be - sociated with variations in shape, and hence the “shading” in the image can be exploited to infer the “shape” of the scene (shape from shading). Similarly, if the scene contains (statistically) regular structures, variations in image intensity can be used to infer shape (shape from textures). Shading, texture, cast shadows, - cluding boundaries are all “cues” that can be exploited to infer spatial properties of the scene from a single image, when the underlying assumptions are sat- ?ed. In addition, one can obtain spatial cues from multiple images of the same scene taken with changing conditions. For instance, changes in the image due to a moving light source are used in “photometric stereo,” changes in the image due to changes in the position of the cameras are used in “stereo,” “structure from motion,” and “motion blur. ” Finally, changes in the image due to changes in the geometry of the camera are used in “shape from defocus. ” In this book, we will concentrate on the latter two approaches, motion blur and defocus, which are referred to collectively as “accommodation cues. |

### What people are saying - Write a review

We haven't found any reviews in the usual places.

### Contents

LXXVII | 111 |

LXXVIII | 113 |

LXXIX | 114 |

LXXX | 117 |

LXXXI | 118 |

LXXXII | 120 |

LXXXIII | 121 |

LXXXIV | 124 |

XVII | 11 |

XVIII | 12 |

XX | 14 |

XXI | 16 |

XXII | 18 |

XXIII | 19 |

XXIV | 20 |

XXV | 22 |

XXVI | 23 |

XXVII | 26 |

XXVIII | 28 |

XXIX | 29 |

XXX | 30 |

XXXII | 34 |

XXXIII | 35 |

XXXIV | 37 |

XXXV | 38 |

XXXVI | 39 |

XXXVII | 41 |

XXXVIII | 42 |

XL | 46 |

XLII | 47 |

XLIII | 49 |

XLIV | 50 |

XLV | 53 |

XLVII | 55 |

XLVIII | 58 |

XLIX | 60 |

LI | 61 |

LII | 65 |

LIII | 69 |

LIV | 70 |

LV | 71 |

LVI | 76 |

LIX | 78 |

LX | 79 |

LXI | 87 |

LXII | 88 |

LXIII | 89 |

LXIV | 90 |

LXV | 91 |

LXVI | 92 |

LXVII | 94 |

LXVIII | 95 |

LXIX | 96 |

LXX | 97 |

LXXI | 99 |

LXXIII | 106 |

LXXIV | 107 |

LXXV | 109 |

LXXVI | 110 |

LXXXV | 125 |

LXXXVI | 126 |

LXXXVII | 127 |

LXXXVIII | 129 |

LXXXIX | 131 |

XC | 132 |

XCI | 135 |

XCII | 137 |

XCIII | 138 |

XCV | 141 |

XCVI | 146 |

XCVII | 147 |

XCVIII | 148 |

XCIX | 150 |

C | 151 |

CI | 152 |

CIII | 154 |

CIV | 157 |

CV | 159 |

CVI | 161 |

CVII | 162 |

CVIII | 163 |

CX | 164 |

CXII | 168 |

CXIII | 169 |

CXIV | 170 |

CXV | 171 |

CXVI | 172 |

CXVIII | 174 |

CXIX | 176 |

CXX | 185 |

CXXI | 190 |

CXXII | 191 |

CXXIII | 192 |

CXXIV | 194 |

CXXV | 195 |

CXXVI | 197 |

CXXVII | 200 |

CXXVIII | 202 |

CXXIX | 212 |

CXXX | 221 |

CXXXI | 229 |

CXXXII | 232 |

CXXXIII | 234 |

CXXXIV | 235 |

CXXXV | 237 |

CXXXVI | 238 |

CXXXVII | 239 |

247 | |

### Other editions - View all

3-D Shape Estimation and Image Restoration: Exploiting Defocus and Motion-Blur Paolo Favaro,Stefano Soatto No preview available - 2006 |

3-D Shape Estimation and Image Restoration: Exploiting Defocus and Motion-Blur Paolo Favaro,Stefano Soatto No preview available - 2013 |

### Common terms and phrases

3-D shape algorithm aperture Appendix approximation assume assumption blurred images Bottom-left Bottom-right camera capture chapter compute converges corresponding cost functional cues data set deblurred deﬁned deﬁnition defocused images denotes diffusion coefﬁcient diffusion equation diffusion tensor discrepancy domain equifocal planes Estimated depth map ﬁeld ﬁnite ﬁnite-dimensional ﬁrst fronto-parallel functional derivative Gaussian geometry gradient heat equation I-divergence ill-posed problems image in Figure image plane image restoration imaging model inference input images integral inverse problem iteration kernel L2 norm least-squares lens matrix measured image minimization motion blur motion-blurred images notValid object obtained occluding optical original image orthogonal operators pinhole pixel point-spread function previous section reader real images reconstruction reﬂectance region regularization satisﬁed scene shape and radiance shape from defocus shutter interval singular value decomposition solution strcmp sufﬁcient surface telecentric term thin lens Tikhonov regularization Top-left Top-right unknowns vector velocity visual zero