High Perceptual Quality Image Denoising with a Posterior Sampling CGAN

Guy Ohayon, Theo Adrai, Gregory Vaksman, Michael Elad, Peyman Milanfar

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The vast work in Deep Learning (DL) has led to a leap in image denoising research. Most DL solutions for this task have chosen to put their efforts on the denoiser's architecture while maximizing distortion performance. However, distortion driven solutions lead to blurry results with sub-optimal perceptual quality, especially in immoderate noise levels. In this paper we propose a different perspective, aiming to produce sharp and visually pleasing denoised images that are still faithful to their clean sources. Formally, our goal is to achieve high perceptual quality with acceptable distortion. This is attained by a stochastic denoiser that samples from the posterior distribution, trained as a generator in the framework of conditional generative adversarial networks (CGAN). Contrary to distortion-based regularization terms that conflict with perceptual quality, we introduce to the CGAN objective a theoretically founded penalty term that does not force a distortion requirement on individual samples, but rather on their mean. We showcase our proposed method with a novel denoiser architecture that achieves the reformed denoising goal and produces vivid and diverse outcomes in immoderate noise levels.

Original languageEnglish
Title of host publicationProceedings - 2021 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2021
Pages1805-1813
Number of pages9
ISBN (Electronic)9781665401913
DOIs
StatePublished - 2021
Event18th IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2021 - Virtual, Online, Canada
Duration: 11 Oct 202117 Oct 2021

Publication series

NameProceedings of the IEEE International Conference on Computer Vision
Volume2021-October

Conference

Conference18th IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2021
Country/TerritoryCanada
CityVirtual, Online
Period11/10/2117/10/21

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'High Perceptual Quality Image Denoising with a Posterior Sampling CGAN'. Together they form a unique fingerprint.

Cite this