TY - GEN
T1 - SINGLE IMAGE RESTORATION WITH GENERATIVE PRIORS
AU - Basioti, Kalliopi
AU - Moustakides, George V.
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021
Y1 - 2021
N2 - Generative models can be used, as an alternative to conventional probability densities, to capture the statistical behavior of complicated datasets. Unlike probability densities with which the generation of realizations may become a challenging task, generative models have an inherent ability to easily produce realizations, which, in the case of natural images can be extremely realistic. In many image restoration problems, such as deblurring, colorization, inpainting, super-resolution, etc., probability densities are used as priors, one may therefore wonder whether we can, instead, adopt generative models. Indeed such methods have appeared in the literature, but they require exact knowledge of the transformations responsible for the data distortion and involve regularizer terms with weights that require adjustment. Our approach, by combining maximum a-posteriori probability with maximum likelihood estimation, can successfully restore images in both blind and non-blind modes without the need to fine-tune any regularization parameters. Simulations on deblurring, colorization, and image separation problems with exact knowledge of the transformation demonstrate improved image quality, reduced computational cost compared to existing methods. Comparable results are also enjoyed when the distortion models contain unknown parameters.
AB - Generative models can be used, as an alternative to conventional probability densities, to capture the statistical behavior of complicated datasets. Unlike probability densities with which the generation of realizations may become a challenging task, generative models have an inherent ability to easily produce realizations, which, in the case of natural images can be extremely realistic. In many image restoration problems, such as deblurring, colorization, inpainting, super-resolution, etc., probability densities are used as priors, one may therefore wonder whether we can, instead, adopt generative models. Indeed such methods have appeared in the literature, but they require exact knowledge of the transformations responsible for the data distortion and involve regularizer terms with weights that require adjustment. Our approach, by combining maximum a-posteriori probability with maximum likelihood estimation, can successfully restore images in both blind and non-blind modes without the need to fine-tune any regularization parameters. Simulations on deblurring, colorization, and image separation problems with exact knowledge of the transformation demonstrate improved image quality, reduced computational cost compared to existing methods. Comparable results are also enjoyed when the distortion models contain unknown parameters.
KW - Bayes procedures
KW - Blind image restoration/separation
KW - Generative modeling
KW - Image restoration
KW - Image separation
UR - http://www.scopus.com/inward/record.url?scp=85125560430&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85125560430&partnerID=8YFLogxK
U2 - 10.1109/ICIP42928.2021.9506768
DO - 10.1109/ICIP42928.2021.9506768
M3 - Conference contribution
AN - SCOPUS:85125560430
T3 - Proceedings - International Conference on Image Processing, ICIP
SP - 1679
EP - 1683
BT - 2021 IEEE International Conference on Image Processing, ICIP 2021 - Proceedings
PB - IEEE Computer Society
T2 - 28th IEEE International Conference on Image Processing, ICIP 2021
Y2 - 19 September 2021 through 22 September 2021
ER -