Infrared and visible image fusion based on visual saliency map and weighted least square optimization

By Jinlei Ma, Zhiqiang Zhou, Bo-tao Wang, Hua Zong. 2017

708 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/a8ca5273b00f8a6021b2c78fd1be422a3b14b931

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. Xiaojun Wu
4. Linfeng Tang
5. Josef Kittler
6. Yiannis Demiris
7. Xingchen Zhang
8. Hao Zhang

In Media Technology

1. Hui Li
2. Jiayi Ma
3. Linfeng Tang
4. Xiaojun Wu
5. Yiannis Demiris
6. Xingchen Zhang
7. Josef Kittler
8. Han Xu

Citations in the corpus

• Infrared and Visible Image Fusion using a Deep Learning Framework (2018, methodology): “In our experiment, the source infrared and visible images were collected from [20] and [25].”
• Infrared and Visible Image Fusion with ResNet and zero-phase component analysis (2018, methodology): “We collect 21 pairs of source infrared and visible images from [28] and [29].”
• Multi-interactive Feature Learning and a Full-time Multi-modality Benchmark for Image Fusion and Segmentation (2023, methodology): “To maintains the vital intensity in the fused image, we employ the saliency-based pixel loss, it formulated as : where m 1 and m 2 are saliency weight maps calculated by VSM [44].”
• STDFusionNet: An Infrared and Visible Image Fusion Network Based on Salient Target Detection (2021, methodology): “The abovementioned infrared and visible image fusion methods all have their strengths and weaknesses, and the hybrid models combine their strengths to improve the fusion performance [7], [21].”
• FusionGAN: A generative adversarial network for infrared and visible image fusion (2019, methodology): “They can be simply divided into seven categories including multi-scale transform- [5, 6, 7], sparse representation- [8, 9], neural network- [10, 11], subspace- [12, 13], and saliency-based [14, 15] methods, hybrid models [16, 17], and other methods [18, 19].”
• DATFuse: Infrared and Visible Image Fusion via Dual Attention Transformer (2023, methodology): “To pursue better fusion performance, more complex fusion rules were proposed such as optimization-based rules [42].”
• SuperFusion: A Versatile Image Registration and Fusion Network with Semantic Awareness (2022, background): “More specifically, traditional fusion frameworks involve broadly five categories, i.e. , multi-scale transformation (MST)- based [8], [9], [10], sparsity representation (SR)-based [11], subspace-based [12], saliency-based [13], and optimization-based [14], [15] fusion methods.”
• Target-aware Dual Adversarial Learning and a Multi-scenario Multi-Modality Benchmark to Fuse Infrared and Visible for Object Detection (2022, background): “Traditional multi-scale transform [10, 24], optimization model [16, 20, 41], spare representation [37, 43], and subspace methods attempt to discover intrinsic common features of the two modalities and to design appropriate weighting rules for fusion.”
• GANMcC: A Generative Adversarial Network With Multiclassification Constraints for Infrared and Visible Image Fusion (2021, methodology): “Typical traditional methods are sparse representation-based methods [7], [8], multiscale transform-based methods [9], [10], subspace-based methods [11], saliency-based method [12], [13], and hybrid methods [14], [15].”
• DDcGAN: A Dual-Discriminator Conditional Generative Adversarial Network for Multi-Resolution Image Fusion (2020, background): “…can be divided into different categories, including multi-scale transform-based methods [9], [10], sparse representation-based methods [11], [12], neural network-based methods [13], subspace-based methods [14], saliency-based methods [15], hybrid meth-ods [16], and other fusion methods [17], [18].”
• NestFuse: An Infrared and Visible Image Fusion Architecture Based on Nest Connection and Spatial/Channel Attention Models (2020, methodology): “For GTF, WLS, ConvSR, Vg-gML and FusionGAN, although some of the saliency features are highlighted, some regions in fused images are blurred.”
• MDLatLRR: A Novel Decomposition Method for Infrared and Visible Image Fusion (2018, methodology): “They include: cross bilateral filter method(CBF) [14], discrete cosine harmonic wavelet transform method(DCHWT) [13], joint sparse representation-based method(JSR) [55], the JSR model with saliency detection method(JSRSD) [23], the gradient transfer fusion method(GTF) [30], weighted least square opt”
• DenseFuse: A Fusion Approach to Infrared and Visible Images (2018, neutral): “In our experiment, the number of input images(k) is 2 and the source infrared and visible images were collected from [19] and [20].”