Efficient, Blind, Spatially-Variant Deblurring for Shaken Images

Oliver Whyte 1, 2 Josef Sivic 1, 2 Andrew Zisserman 3 Jean Ponce 1, 2
1 WILLOW - Models of visual object recognition and scene understanding
DI-ENS - Département d'informatique de l'École normale supérieure, ENS Paris - École normale supérieure - Paris, Inria Paris-Rocquencourt, CNRS - Centre National de la Recherche Scientifique : UMR8548
Abstract : In this chapter we discuss modeling and removing spatially-variant blur from photographs. We describe a compact global parameterization of camera shake blur, based on the 3D rotation of the camera during the exposure. Our model uses three-parameter homographies to connect camera motion to image motion and, by assigning weights to a set of these homographies, can be seen as a generalization of the standard, spatially-invariant convolutional model of image blur. As such we show how existing algorithms, designed for spatially-invariant deblurring, can be "upgraded" in a straightforward manner to handle spatially-variant blur instead. We demonstrate this with algorithms working on real images, showing results for blind estimation of blur parameters from single images, followed by non-blind image restoration using these parameters. Finally, we introduce an efficient approximation to the global model, which significantly reduces the computational cost of modeling the spatially-variant blur. By approximating the blur as locally-uniform, we can take advantage of fast Fourier-domain convolution and deconvolution, reducing the time required for blind deblurring by an order of magnitude.
Type de document :
Chapitre d'ouvrage
A. N. Rajagopalan; Rama Chellappa. Motion Deblurring: Algorithms and Systems, Cambridge University Press, 2014
Liste complète des métadonnées

Littérature citée [42 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01063814
Contributeur : Josef Sivic <>
Soumis le : samedi 13 septembre 2014 - 14:45:24
Dernière modification le : jeudi 11 janvier 2018 - 06:23:05
Document(s) archivé(s) le : dimanche 14 décembre 2014 - 10:23:51

Fichier

whyte13.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01063814, version 1

Collections

Citation

Oliver Whyte, Josef Sivic, Andrew Zisserman, Jean Ponce. Efficient, Blind, Spatially-Variant Deblurring for Shaken Images. A. N. Rajagopalan; Rama Chellappa. Motion Deblurring: Algorithms and Systems, Cambridge University Press, 2014. 〈hal-01063814〉

Partager

Métriques

Consultations de la notice

141

Téléchargements de fichiers

478