Deep Learning in Remote Sensing Image Fusion: Methods, protocols, data, and future perspectives

Image fusion can be conducted at different levels, with pixel-level image fusion involving the direct combination of original information from source images. The objective of methods falling under this category is to generate a fused image that enhances both visual perception and subsequent processing tasks. This survey article draws upon research findings in pixel-level image fusion for remote sensing, outlining primary research directions, such as image sharpening, multimodal image fusion, and spatiotemporal image fusion. For each area, state-of-the-art deep learning (DL) solutions are deeply reviewed. Furthermore, this article discusses open issues and potential future directions. It also examines common downstream image fusion tasks to underscore how they can benefit from image fusion techniques to achieve improved performance. This article aims to extend beyond a conventional survey by not only reviewing existing methodologies but also providing practical insights, such as assessment protocols, available datasets for training and testing DL models, and guidelines for DL remote sensing image fusion. This article is geared toward students and professionals who want to approach pixel-level image fusion in remote sensing, offering valuable cues and tools for addressing specific challenges. The authors wish this work to contribute to reducing barriers to entry for interested scientists in adjacent research fields and aid the growth of a new generation of image fusion researchers.