Article Dans Une Revue Image Processing On Line Année : 2022

Breaking down Polyblur: Fast Blind Correction of Small Anisotropic Blurs

Résumé

Polyblur is a two stage blind deblurring technique for removing small-sized blurs, like small camera shake or the lens point-spread function, proposed in 2021 by Delbracio et al. First, the blur is modeled with a zero-mean anisotropic Gaussian kernel whose parameters are rapidly estimated from the oriented blurry image gradients. Second, a sharp estimate is obtained by applying an approximate deconvolution filter, which is designed as a polynomial function of the estimated blurring kernel. Since in practice true blurs are not exactly Gaussian filters, the residual blur is gradually removed by repeating this two-stage procedure. Because it relies only on simple image manipulations, Polyblur is a quick blind deblurring technique, running in a fraction of a second on a smartphone. In this presentation, we analyze its key ingredients, showcase several use cases on real images, and provide Numpy and Pytorch implementations.

Fichier principal
Vignette du fichier
article.pdf (8.89 Mo) Télécharger le fichier
Origine Fichiers éditeurs autorisés sur une archive ouverte
Licence

Dates et versions

hal-04291108 , version 1 (21-11-2023)

Licence

Identifiants

Citer

Thomas Eboli, Jean-Michel Morel, Gabriele Facciolo. Breaking down Polyblur: Fast Blind Correction of Small Anisotropic Blurs. Image Processing On Line, 2022, 12 (14), pp.435 - 456. ⟨10.5201/ipol.2022.405⟩. ⟨hal-04291108⟩
142 Consultations
187 Téléchargements

Altmetric

Partager

  • More