Infrared and visible image fusion with convolutional neural networks

By Yu Liu, Xun Chen, Juan Cheng, Hu Peng, Zengfu Wang. Int. J. Wavelets Multiresolution Inf. Process., 2017

417 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Media Technology

View Paper: https://www.semanticscholar.org/paper/aa8456f4f4271e7dcbc4cda2ccdbe0a0bc63efbe

How researchers see this paper

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

In Aerospace Engineering

1. Han Xu
2. Junjun Jiang
3. Jiayi Ma
4. Y. Liu
5. Fazhi He
6. Wei Tang
7. Guobao Xiao
8. Linfeng Tang

In Media Technology

1. Jiayi Ma
2. Yiannis Demiris
3. Xingchen Zhang
4. Linfeng Tang
5. Hao Zhang
6. Hui Li
7. Han Xu
8. Wei Tang

Citations in the corpus

• FusionGAN: A generative adversarial network for infrared and visible image fusion (2019, methodology): “[26] trained a deep convolutional neural network (CNN) to jointly generate activity level measurement and fusion rule, and they also applied their model to fuse infrared and visible images [27].”
• Using labeled data to evaluate change detectors in a multivariate streaming environment (2009, positive): “FastSCNN [18] adopts the skip connection in the deep convolutional neural network and proposes a shallow learning module to downsam-ple for fast and efficient multi-branch low-level feature extraction.”
• STDFusionNet: An Infrared and Visible Image Fusion Network Based on Salient Target Detection (2021, methodology): “Liu et al. [10] adopted a pretrained CNN to implement activity level measurement of source images and generate a weight map, in which the whole fusion process is based on pyramids.”
• DATFuse: Infrared and Visible Image Fusion via Dual Attention Transformer (2023, positive): “Liu et al. [52] introduced a CNN to address the infrared and visible image fusion issue, where a Siamese convolutional network is adopted for weight map generation.”
• AttentionFGAN: Infrared and Visible Image Fusion Using Attention-Based Generative Adversarial Networks (2021, background): “Liu et al. employed the siamese convolutional network to take the activity level measurement and weight assignment problems as a whole to fuse infrared and visible image [26].”
• GANMcC: A Generative Adversarial Network With Multiclassification Constraints for Infrared and Visible Image Fusion (2021, methodology): “In particular, Liu et al. [37] proposed a method based on CNN for infrared and visible image fusion.”
• Visible and Infrared Image Fusion Using Deep Learning (2023, methodology): “When deep learning was introduced to VIF, only DBM [21] and CNN [29], [30], [41] were applied to perform VIF.”
• YDTR: Infrared and Visible Image Fusion via Y-Shape Dynamic Transformer (2023, methodology): “Liu et al. [25] first applied a CNN to infrared and visible image fusion field, where a Siamese convolutional network was utilized to achieve activity level measurement and weight assignment as a whole.”