Image fusion meets deep learning: A survey and perspective

By Hao Zhang, Han Xu, Xin Tian, Junjun Jiang, Jiayi Ma. Information Fusion, 2021

753 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/af49c3e63b1e20310d8cf7badd87f4cf2944c649

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Yiannis Demiris
2. Xingchen Zhang
3. Hui Li
4. Jiayi Ma
5. Linfeng Tang
6. Xiao-Jun Wu
7. Yong Ma
8. Jun Huang

In Media Technology

1. Yiannis Demiris
2. Xingchen Zhang
3. Hui Li
4. Jiayi Ma
5. Linfeng Tang
6. Xiao-Jun Wu
7. Danfeng Hong
8. Yong Ma

Citations in the corpus

• CrossFuse: A novel cross attention mechanism based infrared and visible image fusion approach (2024, background): “However, in image fusion fields, particularly multimodal image fusion, complementary (uncorrelation) information is crucial [3][4].”
• Infrared and Visible Image Fusion via Decoupling Network (2022, methodology): “However, these methods with handcrafted fusion rules make it face the same problems as traditional methods, i.e., the existence of incomplete fusion feature representation [18].”
• YDTR: Infrared and Visible Image Fusion via Y-Shape Dynamic Transformer (2023, methodology): “Generally, MST-based methods consist of three main steps [34]–[36]: (i) The source images are decomposed to obtain multi-scale sub-bands.”
• Deep Multimodal Data Fusion (2024, background): “Compared to the existing surveys [2, 4, 45, 46, 121, 128, 227, 235, 243] that usually focus on one single task (such as multimodal object recognition) with one specific combination of two modalities (such as RGB+depth data), this survey owns a broader scope covering various modalities and their…”
• Deep Learning in Multimodal Remote Sensing Data Fusion: A Comprehensive Review (2022, methodology): “The initialization can be the MS image at hand (Fu et al., 2019; Han et al., 2019a; Li et al., 2022a), a random tensor (Uezato et al., 2020; Liu et al., 2021), and a specially learned code (Zhang et al., 2021c, 2020a).”
• Visible and Infrared Image Fusion Using Deep Learning (2023, background): “Zhang et al. [40] did very useful work reviewing deep learning-basedimagefusionmethods,howeverwithoutfocusing onVIF.”
• SuperFusion: A Versatile Image Registration and Fusion Network with Semantic Awareness (2022, background): “To assist humans and machines in comprehensively perceiving the imaging scene, image fusion, an essential image enhancement technique, extracts complementary and useful information from multiple source images and then synthesizes a fused image [2], [3], [4], [5].”
• SwinFusion: Cross-domain Long-range Learning for General Image Fusion via Swin Transformer (2022, background): “O WING to the limitations of hardware devices, information captured by a single-type sensor or with a single shooting setting cannot comprehensively characterize the imaging scenario [1].”