文献类型：期刊文献

英文题名：A review on multi-focus image fusion using deep learning

作者：Luo, Fei[1,2];Zhao, Baojun[1];Fuentes, Joel[3];Zhang, Xueqin[1,2];Ding, Weichao[1];Gu, Chunhua[1];Pino, Luis Rojas[4]

机构：[1]East China Univ Sci & Technol, Sch Informat Sci & Engn, Shanghai 200237, Peoples R China;[2]Shanghai Dev Ctr Comp Software Technol, Shanghai Key Lab Comp Software Evaluating & Testin, Shanghai 201203, Peoples R China;[3]Univ Bio Bio, Dept Comp Sci & Informat Technol, Chillan 3780000, Chile;[4]Univ San Sebastian, Sch Engn Architecture & Design, Santiago 8320000, Chile

年份：2025

卷号：618

外文期刊名：NEUROCOMPUTING

收录：;EI(收录号：20245017517793);WOS:【SCI-EXPANDED(收录号:WOS:001385465100001)】；

基金：This research was supported by the General program of National Nature Science Foundation of China (62276097) , Nature Science Foundation of Shanghai, China (22ZR1416500) , Shanghai Sailing Program, China (20YF1410900) , "Science and Technology Innovation Action Plan" The Yangtze River Delta Science, China and Technology Communication Alliance Shanghai 2021, China (Grant No. 21002411000) , Nature Science Foundation of Shanghai, China (23ZR1414900) .

语种：英文

外文关键词：Image enhancement technique; MFIF; Deep learning; Most-frequently-used datasets; Statistics about evaluation metrics

摘要：Multi-focus image fusion (MFIF) is an image enhancement technique that investigates how to obtain a fully focused image from multiple defocus images, providing fundamental services for computer vision fields, such as image recognition, 3D reconstruction, medical diagnosis, computational photography, etc. In recent years, the deep learning-based MFIF has broken through the limitations of traditional MFIF and achieved superior fusion results. Existing reviews on MFIF mainly classify and describe the techniques at the technical level, such as supervised/unsupervised learning methods and network types, but lack discussion and analysis on problem scenarios. Therefore, based on the problem scenarios of MFIF, this paper categorizes deep learning-based MFIF research into six types: MFIF with lightweight networks, MFIF for artifacts and defocus spread effects, MFIF for information preservation, MFIF with unified fusion networks, MFIF on addressing suboptimal initial decision map and MFIF in challenging environments. Furthermore, this paper summarizes commonly used synthesis datasets and real datasets for MFIF, and statistically describes the main evaluation metrics. Finally, this paper analyzes the shortcomings of existing algorithms, and identifies potential future research directions, aiming to provide objective reviews for MFIF researchers focusing on different problem scenarios.