A comprehensive survey on image fusion: Which approach fits which need

计算机科学 图像(数学) 融合 人工智能 图像融合 计算机视觉 数据科学 语言学 哲学
作者
Gwendal Bernardi,Godefroy Brisebarre,Sébastien Roman,Mohsen Ardabilian,Emmanuel Dellandréa
出处
期刊:Information Fusion [Elsevier BV]
卷期号:126: 103594-103594 被引量:3
标识
DOI:10.1016/j.inffus.2025.103594
摘要

Image fusion is a fundamental task in computer vision that involves combining information from multiple images to produce a more informative and consistent representation. Once the relevant features are identified, they are fused to achieve specific application goals. The field of image fusion encompasses several categories, including multi-focus, multi-exposure, multi-modal, and multi-view fusion. Most state-of-the-art solutions focus on optimizing methods to address a specific fusion category (e.g., multi-view, multi-modal, multi-exposure, or multi-focus). However, some use cases require universal methods capable of handling all these challenges. While recent advancements, particularly in deep learning, have achieved remarkable results within individual categories, the growing need for general-purpose solutions across diverse fusion tasks calls for a broader perspective. This survey provides a comprehensive and unified review of image fusion techniques, systematically covering all four major categories. Special attention is given to deep learning-based methods, which have become dominant in recent years across various fusion types. A key contribution of this work is the integration of multi-view image fusion, often overlooked in prior surveys, with other fusion approaches. We introduce a novel taxonomy that distinguishes between mono-category methods, which target a single fusion domain, and multi-category methods, which are capable of addressing multiple fusion types. Particular emphasis is placed on generalist multi-category approaches, which handle cross-domain scenarios and represent a promising line of research. Additionally, this survey provides practical guidance through summaries of available datasets, evaluation metrics, and representative methods. By offering this structured overview and highlighting unexplored directions, the survey serves as both a foundational reference and a roadmap for future research on unified and adaptive deep learning-based image fusion techniques. • Classification of fusion methods into mono- and multi-category approaches. • Identification of multi-category fusion methods with unified architectures. • Evaluation of fusion performance using benchmark datasets and objective metrics. • Discussion of challenges in generalization, interpretability, and multi-view fusion.
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
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
田様应助俊逸的山蝶采纳,获得10
刚刚
Shafiq完成签到,获得积分10
刚刚
1秒前
1秒前
1秒前
Murphy发布了新的文献求助10
1秒前
乐乐应助Eina采纳,获得10
1秒前
小马甲应助后来采纳,获得10
1秒前
开心的曲奇完成签到,获得积分10
2秒前
Owen应助nekoneko采纳,获得10
2秒前
六时月关注了科研通微信公众号
3秒前
王啵啵发布了新的文献求助10
4秒前
5秒前
萌萌发布了新的文献求助10
5秒前
科研通AI6.4应助panyanjun采纳,获得10
5秒前
王小花发布了新的文献求助10
5秒前
utopia发布了新的文献求助10
5秒前
5秒前
科研通AI6.4应助dejiangcj采纳,获得10
6秒前
6秒前
popkeke完成签到,获得积分10
8秒前
汉堡包应助cm5257采纳,获得10
8秒前
天天快乐应助yang采纳,获得10
8秒前
小琳琳呀发布了新的文献求助10
9秒前
丘比特应助五条悟采纳,获得10
9秒前
10秒前
圈圈发布了新的文献求助10
10秒前
Moonber发布了新的文献求助10
10秒前
Lucas应助song采纳,获得10
10秒前
10秒前
orixero应助小呆采纳,获得10
10秒前
10秒前
智慧爷爷完成签到,获得积分10
11秒前
脑袋瓜发布了新的文献求助10
11秒前
情怀应助阳光怀亦采纳,获得10
12秒前
12秒前
打打应助miao采纳,获得10
12秒前
12秒前
12秒前
王兵完成签到,获得积分20
12秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
2026年中国辛酸癸酸聚乙二醇甘油酯行业市场现状调查及投资机会研判报告 1000
2026年中国辛酸癸酸聚乙二醇甘油酯行业市场规模及竞争格局分析报告 1000
Resiliency Scale for Adolescents--Chinese Version 800
Fundamentals of Pharmaceutical and Biologics Regulations: A Global Perspective, Second Edition 700
作者名:Kristopher P. Plain,悉尼大学的,目前只能查到其四篇论文,想找到其博士论文 550
Matrix Methods in Data Mining and Pattern Recognition Second Edition 510
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 工程类 有机化学 化学工程 生物化学 计算机科学 内科学 物理 复合材料 催化作用 细胞生物学 无机化学 光电子学 物理化学 电极 基因
热门帖子
关注 科研通微信公众号,转发送积分 7327677
求助须知:如何正确求助?哪些是违规求助? 8942393
关于积分的说明 18966331
捐赠科研通 6983642
什么是DOI,文献DOI怎么找? 3216154
关于科研通互助平台的介绍 2382980
邀请新用户注册赠送积分活动 2195515