A new image fusion performance metric based on visual information fidelity

By Yu Han, Yunze Cai, Yin Cao, Xiaoming Xu. Information Fusion, 2013

1,001 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/0b14bc20e782eab640f0f491f644d5369589c0a5

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. Jiayi Ma
2. Hui Li
3. Han Xu
4. Hao Zhang
5. Linfeng Tang
6. Junjun Jiang
7. Xiaojun Wu
8. Xiaoguang Mei

In Media Technology

1. Jiayi Ma
2. Hui Li
3. Han Xu
4. Hao Zhang
5. Linfeng Tang
6. Junjun Jiang
7. Xiaojun Wu
8. Pengwei Liang

Citations in the corpus

• Image Fusion With Convolutional Sparse Representation (2016, methodology): “Four popular objective metrics, namely, the entropy EN, the gradient-based metric QAB/F [35], the HVS-based metric QHVS [36] and the visual information fidelity fusion metric VIFF [37], are adopted to evaluate fusion performance.”
• DDcGAN: A Dual-Discriminator Conditional Generative Adversarial Network for Multi-Resolution Image Fusion (2020, methodology): “Eight metrics such as entropy (EN) [50], mean gradient (MG), spatial frequency (SF), standard deviation (SD) [51], peak signal-to-noise ratio (PSNR), and correlation coefficient (CC), structural similarity index measure (SSIM) [52] and visual information fidelity (VIF) [53] are used for evaluation.”
• STDFusionNet: An Infrared and Visible Image Fusion Network Based on Salient Target Detection (2021, methodology): “Quantitative comparisons of the four metrics, i.e., EN, MI, VIF, and SF, on 20 image pairs from the TNO dataset.”
• LLVIP: A Visible-infrared Paired Dataset for Low-light Vision (2021, methodology): “VIFF [6] utilizes the models in VIF to capture visual information from the two source fused pairs.”
• A medical image fusion method based on convolutional neural networks (2017, background): “They are the information entropy (EN ) of the fused image, the feature mutual information (FMI) [29], Xydeas-Petrovic’s gradient based metric QG [30], Piella-Heijmans’s similarity based metric QE [31], and the visual information fidelity fusion (V IFF ) metric [32].”
• FusionGAN: A generative adversarial network for infrared and visible image fusion (2019, background): “C C E P VIF measures the information fidelity of the fused image, and it is computed by four steps: firstly, the source images and fused image are divided into different blocks; then, evaluate the visual information of each block with and without distortion; subsequently, evaluate the VIF for each sub-”