Image Fusion With Convolutional Sparse Representation

By Yu Liu, Xun Chen, Rabab Kreidieh Ward, Z. J. Wang. IEEE Signal Processing Letters, 2016

870 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/9194b6eb61f45ee76b98b3bd72b5d4bb1efbb3e9

How researchers see this paper

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

In Biomedical Engineering

1. Hui Li
2. Xiaojun Wu
3. Josef Kittler
4. Jiayi Ma
5. Xiao-Jun Wu
6. Linfeng Tang
7. Hao Zhang
8. Tariq Salim Durrani

In Computer Vision and Pattern Recognition

1. Jiayi Ma
2. Hui Li
3. Xiaojun Wu
4. Josef Kittler
5. Linfeng Tang
6. Han Xu
7. Hao Zhang
8. Xiao-Jun Wu

In Media Technology

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

Citations in the corpus

• RFN-Nest: An end-to-end residual fusion network for infrared and visible images (2021, methodology): “To compare the fusion performance of the proposed method with the state-of-the-art algorithms, eleven representative fusion methods are chosen, including discrete cosine harmonic wavelet transform(DCHWT) [50], gradient transfer and total variation minimization(GTF) [53], convolutional sparse represe”
• 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”
• A medical image fusion method based on convolutional neural networks (2017, methodology): “In image fusion research, sparse representation is another popular image modelling approach, which has also been successfully applied to fuse multi-modal medical images [4], [5], [15], [22].”
• DATFuse: Infrared and Visible Image Fusion via Dual Attention Transformer (2023, methodology): “In addition, SR has been widely adopted in the image fusion community, including joint sparse representation (JSR)-based methods [43] and convolutional sparse representation (CSR)-based meth-ods [44].”
• DenseFuse: A Fusion Approach to Infrared and Visible Images (2018, methodology): “The convolutional neural network(CNN) is used to obtain the image features and reconstruct the fused image [12], [13].”
• DDcGAN: A Dual-Discriminator Conditional Generative Adversarial Network for Multi-Resolution Image Fusion (2020, methodology): “[19] applied the convolutional sparse representation (CSR) for image fusion, which is employed to extract multi-layer features and these features are used to generate the fused image.”
• FusionGAN: A generative adversarial network for infrared and visible image fusion (2019, background): “[29] introduced the convolution sparse representation for image fusion, in which deconvolutional networks intend to build a hierarchy of layers, and each layer consists of an encoder and a decoder.”
• CrossFuse: A novel cross attention mechanism based infrared and visible image fusion approach (2024, methodology): “…the visual information fusion task and many milestone achievements have been made, such as multi-scale transformer [5] [6], sparse representation [7][8], pre-trained deep learning models [9][10], Bayesian based fusion model [11]. multimodal image fusion also has numerous applications in other…”