Multiresolution mixture generative adversarial network for image super-resolution

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

Abstract

With regard to the problem of image super-resolution (SR), generative adversarial network (GAN) can make generated images have more details and better effect on perceptual quality than other methods. However, GAN-based methods may lose the contour of object in some texture-intensive areas. In order to recover contour better and further enhance perceptual quality, we propose a Multiresolution Mixture Generative Adversarial Network for Image Super-Resolution (MRMGAN), which employs a multiresolution mixture network (MRMNet) for image super-resolution. The MRMNet is able to have multiple resolution feature maps at the same time when training. Meanwhile, we propose a residual fluctuation loss, which aims to reduce the overall fluctuation of residual between SR image and high-resolution (HR) image. We evaluated the proposed method on benchmark datasets. Experimental results show that the proposed MRMGAN can get satisfactory performance.

Original languageEnglish
Title of host publication2020 IEEE International Conference on Multimedia and Expo, ICME 2020
PublisherIEEE Computer Society
ISBN (Electronic)9781728113319
DOIs
StatePublished - Jul 2020
Event2020 IEEE International Conference on Multimedia and Expo, ICME 2020 - London, United Kingdom
Duration: 6 Jul 202010 Jul 2020

Publication series

NameProceedings - IEEE International Conference on Multimedia and Expo
Volume2020-July
ISSN (Print)1945-7871
ISSN (Electronic)1945-788X

Conference

Conference2020 IEEE International Conference on Multimedia and Expo, ICME 2020
Country/TerritoryUnited Kingdom
CityLondon
Period6/07/2010/07/20

Keywords

  • Generative adversarial network
  • Multi-resolution mixture network
  • Residual fluctuation loss
  • Super-resolution

Fingerprint

Dive into the research topics of 'Multiresolution mixture generative adversarial network for image super-resolution'. Together they form a unique fingerprint.

Cite this