基于注意力机制的无监督GAN多聚焦图像融合

蒋云峰; 李伟彤

doi:10.12052/gdutxb.240097

欢迎来到能源电力期刊网！

English Version 期刊登录

您当前的位置：

首页 >

文章列表页 >

基于注意力机制的无监督GAN多聚焦图像融合

计算机科学与技术 | 更新时间：2026-05-27

- 基于注意力机制的无监督GAN多聚焦图像融合
- Unsupervised GAN Multi-focus Image Fusion Based on Attention Mechanism
- 广东工业大学学报 2025年42卷第5期页码：112-120
- 作者机构：
  
  广东工业大学信息工程学院,广东,广州,51000
- 作者简介：
  
  蒋云峰(1998–) ，男，硕士研究生，主要研究方向为图像融合，E-mail：jiangyunfeng02@163.com
  李伟彤(1969–) ，男，副教授，主要研究方向为图像处理，E-mail：liweitong@gdut.edu.cn
- 基金信息：
  
  广东省科技计划项目(2017A010101016)
- DOI：10.12052/gdutxb.240097
  中图分类号： TP391
- 纸质出版：2025
- 稿件说明：
移动端阅览
蒋云峰, 李伟彤. 基于注意力机制的无监督GAN多聚焦图像融合[J]. 广东工业大学学报, 2025, 42(5): 112–120.

Jiang Yunfeng, Li Weitong. Unsupervised GAN Multi-focus Image Fusion Based on Attention Mechanism[J]. 2025, 42(5): 112-120.
蒋云峰, 李伟彤. 基于注意力机制的无监督GAN多聚焦图像融合[J]. 广东工业大学学报, 2025, 42(5): 112–120. DOI： 10.12052/gdutxb.240097

Jiang Yunfeng, Li Weitong. Unsupervised GAN Multi-focus Image Fusion Based on Attention Mechanism[J]. 2025, 42(5): 112-120. DOI： 10.12052/gdutxb.240097.

摘要

针对现有多聚焦图像融合方法在聚焦和散焦区域出现边界模糊、信息丢失等问题，提出了一个无监督生成对抗网络。通过复合注意力特征提取模块构成生成器，充分提取源图像的全局和局部特征，加强对图像颜色信息的学习；利用源图像的联合梯度作为鉴别器的输入，增强其纹理细节的提取；结合结构相似度和峰值信噪比提出了结构感知损失，进一步提高融合图像质量。Lytro数据集的实验结果表明：与7种代表性的融合算法相比，该方法在主客观评价方面均取得了良好的融合性能，其中指标PSNR、AG、SF、EI达到了52.38、8.25、22.74、85.96，分别比次优算法提高了5.5%、2.2%、1.4%、2.1%。

Abstract

An unsupervised generative adversarial network is proposed to solve the problems of boundary blurring and information loss in the focusing and defocusing regions of existing multi-focus image fusion methods. By constructing a generator with complex attention feature extraction module

the global and local features of the source image can be fully extracted and the learning of image color information can be strengthened. The combined gradient of the source image is used as the input of the discriminator to enhance the extraction of texture details. Combined with structural similarity and peak signal-to-noise ratio

the structure perception loss is proposed to further improve the quality of the fused image. The experimental results of Lytro data set show that

compared with 7 representative fusion algorithms

this method achieves good fusion performance in both subjective and objective evaluation

among which the indices PSNR

and EI reach 52.38

8.25

22.74

and 85.96

respectively

representing improvements of 5.5%

2.2%

1.4%

and 2.1% over the second-best algorithm.

关键词

Keywords

references

MA J, MA Y, LI C. Infrared and visible image fusion methods and applications: a survey[J]. Information Fusion, 2019, 45: 153-178.

PETSCHNIGG G, SZELISKI R, AGRAWALA M, et al . Digital photography with flash and no-flash image pairs[J ] . ACM Transactions on Graphics (TOG) , 2004, 23(3): 664-672.

WANG H, RIVENSON Y, JIN Y, et al . Deep learning enables cross-modality super-resolution in fluorescence microscopy[J ] . Nature Methods, 2019, 16(1): 103-110.

RIVENSON Y, ZHANG Y, GUNAYDIN H, et al . Phase recovery and holographic image reconstruction using deep learning in neural networks[J ] . Light: Science Applications, 2018, 7(2): 17141-17141.

WANG J W, QU H J, WEI Y N, et al . Multi-focus image fusion method combining linear sparse representation and image matting[J ] . Application Research of Computers, 2022, 39(6): 1879-1885.

LIU Y, LIU S, WANG Z. Multi-focus image fusion with dense SIFT[J]. Information Fusion, 2015, 23: 139-155.

WANG L, QI Z Z, LIU Y. The review of multi-focus image fusion methods based on deep learing[J]. Journal of Image and Graphics, 2023, 28(1): 80-101.

LIU Y, WANG L, CHENG J, et al . Multi-focus image fusion: a survey of the state of the art[J ] . Information Fusion, 2020, 64: 71-91.

ZHANG X. Deep learning-based multi-focus image fusion: a survey and a comparative study[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 44(9): 4819-4838.

ZHANG H, XU H, TIAN X, et al . Image fusion meets deep learning: a survey and perspective[J ] . Information Fusion, 2021, 76: 323-336.

GOODFELLOW I, POUGET-ABADIE J, MIRZA M, et al . Generative adversarial networks[J ] . Communications of the ACM, 2020, 63(11): 139-144.

GUO X, NIE R, CAO J, et al . FuseGAN: learning to fuse multi-focus image via conditional generative adversarial network[J ] . IEEE Transactions on Multimedia, 2019, 21(8): 1982-1996.

WANG Y, XU S, LIU J, et al . MFIF-GAN: a new generative adversarial network for multi-focus image fusion[J ] . Signal Processing: Image Communication, 2021, 96: 116295.

HUANG J, LE Z, MA Y, et al . A generative adversarial network with adaptive constraints for multi-focus image fusion[J ] . Neural Computing and Applications, 2020, 32: 15119-15129.

LI H, ZHANG L M, JIANG M R, et al . Multi-focus image fusion algorithm based on supervised learning for fully convolutional neural networ ks[J ] . Laser Optoelectronics Progress, 2020, 57(8): 081015.

ZHANG H, LE Z, SHAO Z, et al . MFF-GAN: an unsupervised generative adversarial network with adaptive and gradient joint constraints for multi-focus image fusion[J ] . Information Fusion, 2021, 66: 40-53.

XU H, MA J, JIANG J, et al . U2Fusion: a unified unsupervised image fusion network[J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 44(1): 502-518.

HUANG G, LIU Z, VAN DER MAATEN L, et al . Densely connected convolutional networks[C ] //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2017: 4700-4708.

ZHOU L, CAI H, GU J, et al . Efficient image super-resolution using vast-receptive-field attention[C ] //European Conference on Computer Vision. Cham: Springer Nature Switzerland, 2022: 256-272.

ZHANG Y, LI K, LI K, et al . Image super-resolution using very deep residual channel attention networks[C ] //Proceedings of the European conference on computer vision (ECCV) . Berlin: Spring Verlag, 2018: 286-301.

WOO S, PARK J, LEE J Y, et al . CBAM: convolutional block attention module[C ] //Proceedings of the European Conference on Computer Vision (ECCV) . Berlin: Spring Verlag, 2018: 3-19.

WANG Z, BOVIK A C, SHEIKH H R, et al . Image quality assessment: from error visibility to structural similarity[J ] . IEEE Transactions on Image Processing, 2004, 13(4): 600-612.

JAGALINGAM P, HEGDE A V. A review of quality metrics for fused image[J]. Aquatic Procedia, 2015, 4: 133-142.

LIN T Y, MAIRE M, BELONGIE S, et al . Microsoft coco: common objects in context[C ] //Computer Vision–ECCV 2014: 13th European Conference. Zurich: Springer International Publishing, 2014: 740-755.

NEJATI M, SAMAVI S, SHIRANI S. Multi-focus image fusion using dictionary-based sparse representation[J]. Information Fusion, 2015, 25: 72-84.

FARID M S, MAHMOOD A, Al-MAADEED S A. Multi-focus image fusion using content adaptive blurring[J]. Information Fusion, 2019, 45: 96-112.

LIU Y, CHEN X, PENG H, et al . Multi-focus image fusion with a deep convolutional ne ural network[J ] . Information Fusion, 2017, 36: 191-207.

ZHANG Y, LIU Y, SUN P, et al . IFCNN: a general image fusion framework based on convolutional neural network[J ] . Information Fusion, 2020, 54: 99-118.

MA B, ZHU Y, YIN X, et al . SESF-Fuse: an unsupervised deep model for multi-focus image fusion[J ] . Neural Computing and Applications, 2021, 33: 5793-5804.

LIU Y, WANG L, LI H, et al . Multi-focus image fusion with deep residual learning and focus property detection[J ] . Information Fusion, 2022, 86: 1-16.

ZHAI H, ZHENG W, OUYANG Y, et al . Multi-focus image fusion via interactive transformer and asymmetric soft sharing[J ] . Engineering Applications of Artificial Intelligence, 2024, 133: 107967.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于隐藏特征的点云模块

块对角引导的多视角一致性学习

基于生成式样本合成的工件缺陷样本数据增强

人工噪声辅助无人机太赫兹安全通信的鲁棒设计

基于路况参数的混合动力机车能量管理策略研究