End-to-End Learning for Joint Image Demosaicing, Denoising and Super-Resolution

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

65 Citations (Scopus)
65 Downloads (Pure)

Abstract

Image denoising, demosaicing and super-resolution are key problems of image restoration well studied in the recent decades. Often, in practice, one has to solve these problems simultaneously. A problem of finding a joint solution of the multiple image restoration tasks just begun to attract an increased attention of researchers. In this paper, we propose an end-to-end solution for the joint demosaicing, denoising and super-resolution based on a specially designed deep convolutional neural network (CNN). We systematically study different methods to solve this problem and compared them with the proposed method. Extensive experiments carried out on large image datasets demonstrate that our method outperforms the state-of-the-art both quantitatively and qualitatively. Finally, we have applied various loss functions in the proposed scheme and demonstrate that by using the mean absolute error as a loss function, we can obtain superior results in comparison to other cases.
Original languageEnglish
Title of host publication2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
PublisherIEEE
Pages3506-3515
Number of pages10
ISBN (Electronic)978-1-6654-4509-2
DOIs
Publication statusPublished - 2021
Publication typeA4 Article in conference proceedings
EventIEEE Computer Society Conference on Computer Vision and Pattern Recognition - , United States
Duration: 20 Jun 202125 Jun 2021

Publication series

NameIEEE Computer Society Conference on Computer Vision and Pattern Recognition
ISSN (Print)1063-6919
ISSN (Electronic)2575-7075

Conference

ConferenceIEEE Computer Society Conference on Computer Vision and Pattern Recognition
Country/TerritoryUnited States
Period20/06/2125/06/21

Keywords

  • Training
  • Superresolution
  • Noise reduction
  • Switches
  • Image restoration
  • Pattern recognition
  • Convolutional neural networks

Publication forum classification

  • Publication forum level 1

Fingerprint

Dive into the research topics of 'End-to-End Learning for Joint Image Demosaicing, Denoising and Super-Resolution'. Together they form a unique fingerprint.

Cite this