PS-GAN: Pseudo Supervised Generative Adversarial Network With Single Scale Retinex Embedding for Infrared and Visible Image Fusion

Currently, ground truth fusion image, fused image contrast, and naturalness are rarely considered in existing infrared and visible image fusion (IVF) methods. In this article, we proposed a pseudosupervised generative adversarial network (GAN) with single scale retinex (SSR) embedding for IVF. First...

Full description

Saved in:
Bibliographic Details
Main Authors: Jin Qi, Deboch Eyob Abera, Jian Cheng
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10783431/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850113920754253824
author Jin Qi
Deboch Eyob Abera
Jian Cheng
author_facet Jin Qi
Deboch Eyob Abera
Jian Cheng
author_sort Jin Qi
collection DOAJ
description Currently, ground truth fusion image, fused image contrast, and naturalness are rarely considered in existing infrared and visible image fusion (IVF) methods. In this article, we proposed a pseudosupervised generative adversarial network (GAN) with single scale retinex (SSR) embedding for IVF. First, a pseudoground truth fusion image conception and its computation method was proposed to solve ground truth fusion image shortage problem. Second, a novel SSR module embedded residual GAN was designed to improve fusion image contrast and naturalness. Finally, a special dense and mixed modal inputting strategy was also proposed for better modal mixed feature extraction. Extensive experimental results on public IVF datasets verified the superior performance of our proposed approach over other representative methods. It was demonstrated that the fused image details, contrast, and naturalness were significantly improved.
format Article
id doaj-art-167a2cc52433495aa8dfebb2a2d1b6f2
institution OA Journals
issn 1939-1404
2151-1535
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
spelling doaj-art-167a2cc52433495aa8dfebb2a2d1b6f22025-08-20T02:37:02ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-01181766177710.1109/JSTARS.2024.350968410783431PS-GAN: Pseudo Supervised Generative Adversarial Network With Single Scale Retinex Embedding for Infrared and Visible Image FusionJin Qi0https://orcid.org/0000-0001-8427-0080Deboch Eyob Abera1Jian Cheng2https://orcid.org/0000-0001-6966-0531School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, ChinaSchool of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, ChinaSchool of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, ChinaCurrently, ground truth fusion image, fused image contrast, and naturalness are rarely considered in existing infrared and visible image fusion (IVF) methods. In this article, we proposed a pseudosupervised generative adversarial network (GAN) with single scale retinex (SSR) embedding for IVF. First, a pseudoground truth fusion image conception and its computation method was proposed to solve ground truth fusion image shortage problem. Second, a novel SSR module embedded residual GAN was designed to improve fusion image contrast and naturalness. Finally, a special dense and mixed modal inputting strategy was also proposed for better modal mixed feature extraction. Extensive experimental results on public IVF datasets verified the superior performance of our proposed approach over other representative methods. It was demonstrated that the fused image details, contrast, and naturalness were significantly improved.https://ieeexplore.ieee.org/document/10783431/Generative adversarial network (GAN)image contrastimage naturalnessinfrared (IR) and visible (VIS) image fusion (IVF)pseudoground truth fusion image (PGI)
spellingShingle Jin Qi
Deboch Eyob Abera
Jian Cheng
PS-GAN: Pseudo Supervised Generative Adversarial Network With Single Scale Retinex Embedding for Infrared and Visible Image Fusion
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Generative adversarial network (GAN)
image contrast
image naturalness
infrared (IR) and visible (VIS) image fusion (IVF)
pseudoground truth fusion image (PGI)
title PS-GAN: Pseudo Supervised Generative Adversarial Network With Single Scale Retinex Embedding for Infrared and Visible Image Fusion
title_full PS-GAN: Pseudo Supervised Generative Adversarial Network With Single Scale Retinex Embedding for Infrared and Visible Image Fusion
title_fullStr PS-GAN: Pseudo Supervised Generative Adversarial Network With Single Scale Retinex Embedding for Infrared and Visible Image Fusion
title_full_unstemmed PS-GAN: Pseudo Supervised Generative Adversarial Network With Single Scale Retinex Embedding for Infrared and Visible Image Fusion
title_short PS-GAN: Pseudo Supervised Generative Adversarial Network With Single Scale Retinex Embedding for Infrared and Visible Image Fusion
title_sort ps gan pseudo supervised generative adversarial network with single scale retinex embedding for infrared and visible image fusion
topic Generative adversarial network (GAN)
image contrast
image naturalness
infrared (IR) and visible (VIS) image fusion (IVF)
pseudoground truth fusion image (PGI)
url https://ieeexplore.ieee.org/document/10783431/
work_keys_str_mv AT jinqi psganpseudosupervisedgenerativeadversarialnetworkwithsinglescaleretinexembeddingforinfraredandvisibleimagefusion
AT debocheyobabera psganpseudosupervisedgenerativeadversarialnetworkwithsinglescaleretinexembeddingforinfraredandvisibleimagefusion
AT jiancheng psganpseudosupervisedgenerativeadversarialnetworkwithsinglescaleretinexembeddingforinfraredandvisibleimagefusion