SINGLE IMAGE RESTORATION WITH GENERATIVE PRIORS

Kalliopi Basioti, George V. Moustakides

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

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.

Original languageEnglish (US)
Title of host publication2021 IEEE International Conference on Image Processing, ICIP 2021 - Proceedings
PublisherIEEE Computer Society
Pages1679-1683
Number of pages5
ISBN (Electronic)9781665441155
DOIs
StatePublished - 2021
Event28th IEEE International Conference on Image Processing, ICIP 2021 - Anchorage, United States
Duration: Sep 19 2021Sep 22 2021

Publication series

NameProceedings - International Conference on Image Processing, ICIP
Volume2021-September
ISSN (Print)1522-4880

Conference

Conference28th IEEE International Conference on Image Processing, ICIP 2021
Country/TerritoryUnited States
CityAnchorage
Period9/19/219/22/21

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Keywords

  • Bayes procedures
  • Blind image restoration/separation
  • Generative modeling
  • Image restoration
  • Image separation

Fingerprint

Dive into the research topics of 'SINGLE IMAGE RESTORATION WITH GENERATIVE PRIORS'. Together they form a unique fingerprint.

Cite this