Self texture transfer networks for low bitrate image compression

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

Abstract

Lossy image compression causes a loss of texture, especially at low bitrate. To mitigate this problem, we propose a novel image compression method that utilizes a reference-based image super-resolution model. We use two image compression models and a self texture transfer model. The image compression models encode and decode a whole input image and selected reference patches. The reference patches are small but compressed with high quality. The self texture transfer model transfers the texture of reference patches into similar regions in the compressed image. The experimental results show that our method can reconstruct accurate texture by transferring the texture of reference patches.

Original languageEnglish
Title of host publicationProceedings - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2021
PublisherIEEE Computer Society
Pages1901-1905
Number of pages5
ISBN (Electronic)9781665448994
DOIs
Publication statusPublished - 2021 Jun
Event2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2021 - Virtual, Online, United States
Duration: 2021 Jun 192021 Jun 25

Publication series

NameIEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
ISSN (Print)2160-7508
ISSN (Electronic)2160-7516

Conference

Conference2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2021
Country/TerritoryUnited States
CityVirtual, Online
Period21/6/1921/6/25

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Self texture transfer networks for low bitrate image compression'. Together they form a unique fingerprint.

Cite this