3-D Shape Estimation and Image Restoration

Exploiting Defocus and Motion Blur

Paolo Favoro, Stefano Soatto

176 pages, parution le 22/01/2007

Ajouter à une liste

Indisponible

Résumé

Images contain information about the spatial properties of the scene they depict. When coupled with suitable assumptions, images can be used to infer three-dimensional information. This useful volume concentrates on motion blur and defocus, which can be exploited to infer the 3-D structure of a scene-as well as its radiance properties-and which in turn can be used to generate novel images with better quality.

3-D Shape Estimation and Image Restoration presents a coherent framework for the analysis and design of algorithms to estimate 3-D shape from defocused and motion blurred images, and to eliminate defocus and motion blur to yield "restored" images. It provides a collection of algorithms that are optimal with respect to the chosen model and estimation criterion.

Topics and Features include:

Comprehensive introduction to guide readers through the different areas of the topic
Basic models of image formation
Discussion of least-squares shape from defocus
Unifying defocus and motion blur
Handling multiple moving objects
Dealing with occlusions
Appendices supply the necessary background in optimization and regularization
Downloads online

Written for readers with interests in image processing and computer vision and with backgrounds in engineering, science or mathematics, this highly practical text/reference is accessible to advanced students or those with a degree that includes basic linear algebra and calculus courses. It can also be seen as a resource for practitioners looking to expand their knowledge in the subject.

Written for: Graduate students in Programming; researchers in Computer Vision and Image Processing

L'auteur - Stefano Soatto

Stefano Soatto: Los Angeles, California

Sommaire

Visual Cues for Shape and Motion
Basic Models of Image Formation
When Can 3D Shape Be Reconstructed from Blurred Images
A First Solution: Least-Squares
Enforcing Positivity
Defocus via Diffusion: Modeling and Reconstruction from Two Views
Shape from the Defocus of Multiple Images
Modeling Motion-Blur and Defocus via Diffusion
Dealing with Occlusions
Conclusions and Open Issues

A. Concepts of Radiometry
B. A PDE Primer
C. Proofs of Propositions
D. Calibration of Defocused Images
E. Matlab Implementation of Some Algorithms

Voir tout

Replier

Caractéristiques techniques

	PAPIER
Éditeur(s)	Springer
Auteur(s)	Paolo Favoro, Stefano Soatto
Parution	22/01/2007
Nb. de pages	176
Format	16 x 24
Couverture	Relié
Poids	570g
Intérieur	Noir et Blanc
EAN13	9781846281761
ISBN13	978-1-84628-176-1