articleIEEE Transactions on Image ProcessingJan 1, 2020Closed access

DDcGAN: A Dual-Discriminator Conditional Generative Adversarial Network for Multi-Resolution Image Fusion

Wuhan University · Harbin Institute of Technology · +1 more institution

PubMed
Indexed incrossrefpubmed

Abstract

In this paper, we proposed a new end-to-end model, termed as dual-discriminator conditional generative adversarial network (DDcGAN), for fusing infrared and visible images of different resolutions. Our method establishes an adversarial game between a generator and two discriminators. The generator aims to generate a real-like fused image based on a specifically designed content loss to fool the two discriminators, while the two discriminators aim to distinguish the structure differences between the fused image and two source images, respectively, in addition to the content loss. Consequently, the fused image is forced to simultaneously keep the thermal radiation in the infrared image and the texture details in…

Citation impact

1,253
total citations
FWCI
101.36
Percentile
100%
References
68
Citations per year

Authors

5

Topics & keywords

Keywords
  • Discriminator
  • Artificial intelligence
  • Dual (grammatical number)
  • Image fusion
  • Computer science
  • Generative adversarial network
  • Adversarial system
  • Image (mathematics)
UN Sustainable Development Goals
  • Reduced inequalities
No related works found for this paper.

Funding