Efficient image fusion with approximate sparse representation

Yang, Bin; Yang, Chao; Guoyu, Huang

doi:10.1142/s0219691316500247

Cited by 49 publications

(17 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Traditional image fusion methods employed discrete cosine transform (DCT) [18], sparse representation (SR) [19], [8], principal component analysis (PCA) [20], etc. to extract useful features.…”

Section: A Image Fusionmentioning

confidence: 99%

“…Traditional methods for image fusion include sparse representation (SR) based methods [8], [9]; multi-scale transformation based methods [10], [11]; saliency-based methods Vibashan VS, Jeya Maria Jose Valanarasu, Poojan Oza, Vishal M. Patel are with Department of Electrical and Computer Engineering in Johns Hopkins University, Baltimore, MD 21218, USA. (e-mail: {vvishnu2, jvalana1, poza2, vpatel36}@jhu.edu).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Image Fusion Transformer

VS¹,

Valanarasu²,

Oza³

et al. 2021

Preprint

View full text Add to dashboard Cite

In image fusion, images obtained from different sensors are fused to generate a single image with enhanced information. In recent years, state-of-the-art methods have adopted Convolution Neural Networks (CNNs) to encode meaningful features for image fusion. Specifically, CNN-based methods perform image fusion by fusing local features. However, they do not consider long-range dependencies that are present in the image. Transformer-based models are designed to overcome this by modeling the long-range dependencies with the help of self-attention mechanism. This motivates us to propose a novel Image Fusion Transformer (IFT) where we develop a transformer-based multi-scale fusion strategy that attends to both local and long-range information (or global context). The proposed method follows a two-stage training approach. In the first stage, we train an auto-encoder to extract deep features at multiple scales. In the second stage, multi-scale features are fused using a Spatio-Transformer (ST) fusion strategy. The ST fusion blocks are comprised of a CNN and a transformer branch which capture local and long-range features, respectively. Extensive experiments on multiple benchmark datasets show that the proposed method performs better than many competitive fusion algorithms. Furthermore, we show the effectiveness of the proposed ST fusion strategy with an ablation analysis. The source code is available at: https://github.com/Vibashan/Image-Fusion-Transformer.

show abstract

Section: A Image Fusionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Image Fusion Transformer

VS¹,

Valanarasu²,

Oza³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…In fact, images contain different details feature richness under different exposure conditions. 15 Thus image details factor C k ðx; yÞ was selected as another key factor of image fusion. Because the Laplacian has rotation invariance, Laplace filter L is selected to extract the detailed features of I gray k ðx; yÞ, and the detail image D k ðx; yÞ of I gray k ðx; yÞ are obtained.…”

Section: Selection Of Image Fusion Weightsmentioning

confidence: 99%

Three-dimensional measurement with reflection suppression based on high-dynamic range images

et al. 2019

View full text Add to dashboard Cite

show abstract

“…In the representation learning domain. The most methods are based on sparse representation such as sparse representation (SR) and gradient histogram (HOG) [7], joint sparse representation (JSR) [8], approximate sparse representation with multi-selection strategy [9], etc.…”

Section: Introductionmentioning

confidence: 99%

A Deep Decomposition Network for Image Processing: A Case Study for Visible and Infrared Image Fusion

Fu¹,

Wu²,

Kittler³

2021

Preprint

View full text Add to dashboard Cite

Image decomposition is a crucial subject in the field of image processing. It can extract salient features from the source image. We propose a new image decomposition method based on convolutional neural network. This method can be applied to many image processing tasks. In this paper, we apply the image decomposition network to the image fusion task. We input infrared image and visible light image and decompose them into three high-frequency feature images and a low-frequency feature image respectively. The two sets of feature images are fused using a specific fusion strategy to obtain fusion feature images. Finally, the feature images are reconstructed to obtain the fused image. Compared with the state-of-the-art fusion methods, this method has achieved better performance in both subjective and objective evaluation.

show abstract

Efficient image fusion with approximate sparse representation

Cited by 49 publications

References 20 publications

Image Fusion Transformer

Image Fusion Transformer

Three-dimensional measurement with reflection suppression based on high-dynamic range images

A Deep Decomposition Network for Image Processing: A Case Study for Visible and Infrared Image Fusion

Contact Info

Product

Resources

About