Infrared and visible image fusion via gradient transfer and total variation minimization

By Jiayi Ma, Chen Chen, Chang Li, Jun Huang. Information Fusion, 2016

999 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/ee2c89c0ff7c9de41d4b9915cf777f7c86d956c3

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. Luc Van Gool
3. Hui Li
4. Radu Timofte
5. Xiaojun Wu
6. Josef Kittler
7. Yiannis Demiris
8. Yulun Zhang

In Media Technology

1. Jiayi Ma
2. Hui Li
3. Yiannis Demiris
4. Xingchen Zhang
5. Radu Timofte
6. Linfeng Tang
7. Luc Van Gool
8. Xiaojun Wu

Citations in the corpus

• Infrared and Visible Image Fusion via Decoupling Network (2022, background): “The emergence of image fusion technology has broken through the limitations of a single sensor, providing sufficient scene information for high-level image processing tasks, such as video surveillance [1] and target recognition [2].”
• DDcGAN: A Dual-Discriminator Conditional Generative Adversarial Network for Multi-Resolution Image Fusion (2020, methodology): “…discriminators and is defined as : As the thermal radiation and texture details are mainly characterized by pixel intensities and gradient variation [17], respectively, we employ the Frobenius norm to constrain the downsampled fused image to have similar pixel intensities with the infrared image as…”
• DDFM: Denoising Diffusion Model for Multi-Modality Image Fusion (2023, methodology): “In addition, following [22, 39], the total variation penalty item r(x) = ‖∇x‖(2)2 can be also added to make the fusion image f better preserve the texture information from v, where∇ denotes the gradient operator.”
• SwinFusion: Cross-domain Long-range Learning for General Image Fusion via Swin Transformer (2022, methodology): “GTF [17], DenseFuse [22], and Fusion-GAN [55] are the three task-specific fusion methods for VIF.”
• GANMcC: A Generative Adversarial Network With Multiclassification Constraints for Infrared and Visible Image Fusion (2021, methodology): “From top to bottom: infrared images, visible images, fused results of LPP [44], LP [45], CVT [46], DTCWT [47], GTF [24], CNN [37], FusionGAN [16], and our GANMcC. and adversarial loss.”
• 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.”
• Rethinking the Image Fusion: A Fast Unified Image Fusion Network based on Proportional Maintenance of Gradient and Intensity (2020, methodology): “Last but not least, although GTF and FusionGAN have larger values on MI, our method achieves a better balance between the information of two source images.”
• DenseFuse: A Fusion Approach to Infrared and Visible Images (2018, methodology): “model(JSR) [9], gradient transfer and total variation minimization(GTF) [23], the JSR model with saliency detection fusion method(JSRSD) [24], deep convolutional neural network-based method(CNN) [13] and the DeepFuse method(DeepFuse) [15].”
• U2Fusion: A Unified Unsupervised Image Fusion Network (2020, methodology): “…methods breaking away from the framework, such as the method based on gradient transfer and total variation minimization for VIS-IR image fusion [19], the multi-exposure image fusion method by optimizing a structural similarity index [20], and the method based on dense SIFT for multi-focus…”
• Content-Based High-Resolution Remote Sensing Image Retrieval via Unsupervised Feature Learning and Collaborative Affinity Metric Fusion (2016, background): “Hence, in addition to high-resolution remote sensing image retrieval, the proposed unsupervised features would probably benefit other tasks in computer vision such as feature matching [45,46], image fusion [47], and target detection [48].”
• LLVIP: A Visible-infrared Paired Dataset for Low-light Vision (2021, methodology): “The GTF experiments are conducted on Intel Core i7-4720HQ CPU.”
• DIDFuse: Deep Image Decomposition for Infrared and Visible Image Fusion (2020, methodology): “In image fusion, the infrared and visible image fusion, a.k.a. IVIF, can be applied to many domains, such as surveillance [Bhatnagar and Liu, 2015], modern military and fire rescue tasks [Lahoud and Susstrunk, 2018; Hu et al. , 2017], face recognition [Ma et al. , 2016] and so on.”
• STDFusionNet: An Infrared and Visible Image Fusion Network Based on Salient Target Detection (2021, methodology): “From left to right: infrared image, visible image, fusion result of a traditional method, GTF [6], fusion result of a deep learning-based method, DenseFuse [9], and result of our proposed STDFusionNet.”
• 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.”