Near-Infrared Image Colorization with Weighted UNet++ and Auxiliary Color Enhancement GAN

Sicong Zhou, Sei Ichiro Kamata*

*Corresponding author for this work

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

Abstract

We propose a novel GAN-based method for near-infrared image colorization. This method innovatively rebalances the color of the colorization image by importing a luminance channel and a feature weight-driven color generator. We set the weighted UNet++ structure in the generator for colorization results with the detail of focal objects. A color enhancement network composed of a deeper luminance network and a colorimetric network is used for global color balance to improve the color quality of the generated color images. Our network is trained and evaluated on two datasets. According to the FID, SSIM and PSNR results, our network performs well, with good recovery effects for both overall color and detailed color and outperforming the current state-of-the-art methods.

Original languageEnglish
Title of host publication2022 7th International Conference on Image, Vision and Computing, ICIVC 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages507-512
Number of pages6
ISBN (Electronic)9781665467346
DOIs
Publication statusPublished - 2022
Event7th International Conference on Image, Vision and Computing, ICIVC 2022 - Xi'an, China
Duration: 2022 Jul 262022 Jul 28

Publication series

Name2022 7th International Conference on Image, Vision and Computing, ICIVC 2022

Conference

Conference7th International Conference on Image, Vision and Computing, ICIVC 2022
Country/TerritoryChina
CityXi'an
Period22/7/2622/7/28

Keywords

  • Colorization
  • Generative Adversarial Network
  • Luminance
  • Near-Infrared
  • UNet++

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Computer Vision and Pattern Recognition
  • Safety, Risk, Reliability and Quality

Fingerprint

Dive into the research topics of 'Near-Infrared Image Colorization with Weighted UNet++ and Auxiliary Color Enhancement GAN'. Together they form a unique fingerprint.

Cite this