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

鉴别器 人工智能 对偶(语法数字) 计算机科学 生成对抗网络 图像融合 对抗制 模式识别(心理学) 图像(数学) 融合 计算机视觉 图像处理 探测器 电信 艺术 语言学 哲学 文学类
作者
Jiayi Ma,Han Xu,Junjun Jiang,Xiaoguang Mei,Xiao–Ping Zhang
出处
期刊:IEEE transactions on image processing [Institute of Electrical and Electronics Engineers]
卷期号:29: 4980-4995 被引量:876
标识
DOI:10.1109/tip.2020.2977573
摘要

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 the visible image. Moreover, to fuse source images of different resolutions, e.g., a low-resolution infrared image and a high-resolution visible image, our DDcGAN constrains the downsampled fused image to have similar property with the infrared image. This can avoid causing thermal radiation information blurring or visible texture detail loss, which typically happens in traditional methods. In addition, we also apply our DDcGAN to fusing multi-modality medical images of different resolutions, e.g., a low-resolution positron emission tomography image and a high-resolution magnetic resonance image. The qualitative and quantitative experiments on publicly available datasets demonstrate the superiority of our DDcGAN over the state-of-the-art, in terms of both visual effect and quantitative metrics. Our code is publicly available at https://github.com/jiayi-ma/DDcGAN.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
海东来应助南瓜气气采纳,获得30
刚刚
西西完成签到 ,获得积分10
刚刚
酷波er应助GQL采纳,获得10
1秒前
tramp应助liu采纳,获得20
1秒前
2秒前
2秒前
3秒前
3秒前
6秒前
英姑应助开心的曼岚采纳,获得10
6秒前
7秒前
缥缈丹云发布了新的文献求助10
7秒前
8秒前
东方清婳发布了新的文献求助10
9秒前
9秒前
9秒前
opalc发布了新的文献求助10
9秒前
科研通AI2S应助dejiangcj采纳,获得10
10秒前
SciGPT应助平安顺遂采纳,获得10
10秒前
orixero应助嬛嬛采纳,获得10
12秒前
坚果发布了新的文献求助10
12秒前
天天快乐应助1027采纳,获得10
13秒前
benbenx发布了新的文献求助10
13秒前
chenting发布了新的文献求助10
13秒前
东方清婳完成签到,获得积分10
15秒前
15秒前
明明完成签到,获得积分10
16秒前
丘比特应助liyiliyi117采纳,获得10
18秒前
syh完成签到,获得积分10
18秒前
ZWK发布了新的文献求助10
18秒前
18秒前
19秒前
20秒前
缥缈丹云完成签到,获得积分10
20秒前
冷酷的若剑完成签到,获得积分10
20秒前
22秒前
所所应助坚果采纳,获得10
23秒前
稳重元冬发布了新的文献求助10
24秒前
24秒前
hohokuz完成签到,获得积分10
24秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Picture Books with Same-sex Parented Families: Unintentional Censorship 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
A Preliminary Study on Correlation Between Independent Components of Facial Thermal Images and Subjective Assessment of Chronic Stress 500
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 360
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3971424
求助须知:如何正确求助?哪些是违规求助? 3516157
关于积分的说明 11181063
捐赠科研通 3251297
什么是DOI,文献DOI怎么找? 1795776
邀请新用户注册赠送积分活动 876012
科研通“疑难数据库(出版商)”最低求助积分说明 805228