Single image super resolution using neighbor embedding and statistical prediction model

Rahiman, V. Abdu; George, Sudhish N.

doi:10.1016/j.compeleceng.2016.12.018

Cited by 15 publications

(4 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…SISR reconstruction attempts to increase LR image resolution without introducing blur or noise. SISR methods are classified into three broad categories: interpolation-based methods [9,10], reconstruction-based methods [11,12], and deep learning-based methods. Interpolation-based methods obtain SR results by computing an interpolation formula that considers known pixels and position relationships around a given point.…”

Section: Introductionmentioning

confidence: 99%

Remote Sensing Image Super-Resolution Using Texture Enhancing Generative Adversarial Network

Shou-Quan Che,

Shou-Quan Che

2023

Journal of Computers

View full text Add to dashboard Cite

<p>Single image super-resolution (SISR) brings excellent improvement in remote sensing applications, which has been widely studied in recent years. A method named TFSRGAN of remote sensing single image super-resolution based on generative adversarial network is proposed in this paper to address the problems of poor reconstruction visual quality and smooth details in traditional algorithms. In the proposed framework, s dense residual connection method is proposed to fuse the deep features from each residual block based on the SRGAN network, and the channel attention mechanism is added into the residual block to combinate the channel information. In addition, the network employs an edge extractor to divide the low-resolution image into low-frequency image and high-frequency image as the input of generator to improve the effect of texture reconstruction. Extensive comparison experiments were performed using AID, UCAS_AOD and China Gaofen-1 datasets, the SR results demonstrate that the proposed TFSRGAN framework outperforms the state-of-the-art algorithms including VDSR, SRGAN and ESRGAN in terms of objective evaluation metrics and subjective visual perception. The ground targets detection experiments represent that the proposed TFSRGAN can significantly improve the effect in remote sensing super-resolution application.</p> <p> </p>

show abstract

Section: Introductionmentioning

confidence: 99%

Remote Sensing Image Super-Resolution Using Texture Enhancing Generative Adversarial Network

Shou-Quan Che,

Shou-Quan Che

2023

Journal of Computers

View full text Add to dashboard Cite

show abstract

“…SR is a highly viable and effective method that can be used to enhance the resolution of digital rock images as much as possible while obtaining a large enough imaging FOV to surpass the limitations of physical imaging hardware (seen in Figure 1). Deep learning-based SR algorithms have become mainstream in recent years with their outstanding performance, outlawing previous traditional classical algorithms, including bicubic interpolation, iterative back-projection (Tekalp et al, 1992), neighborhood embedding method (Rahiman and George, 2017), sparse representation (Yang et al, 2010) Sigmoid is a smoother activation function, as in Equation 2.…”

Section: Introductionmentioning

confidence: 99%

Multi Attention Neural Network for Digital Rock CT Images Super-Resolution

Xing

Yao

Liu

et al. 2022

Preprint

View full text Add to dashboard Cite

High-quality digital rock images are essential for subsequent high-precision numerical simulations. But limited by the imaging capability of computed tomography (CT), high resolution digital rock images with wide imaging field of view (FOV) cannot be acquired simultaneously. To cope with this constraint, we propose a novel Multi Attention Super-Resolution Neural Network (MASR) that enhances the resolution of images with wide FOV. Considering that textures and edges are more crucial in digital rocks, MASR introduces the component attention mechanism of Component Divide-and-Conquer Super-Resolution (CDCSR) model. By redesigning the hourglass network with spatial and channel attention mechanisms, proposing a spatial attention-based mask module, and optimizing the component attention mask calculation process, MASR delivers higher information utilization with fewer parameters and faster training than CDCSR. And we optimize the depth of MASR to trade off speed and superresolution quality. Furthermore, we retrained several state-of-the-art models. Through quantitative evaluations and qualitative visualizations, it is verified that MASR can recover sharper edges while removing noise, and obtain digital rock images with superior quality and reliability. The pixelwise relative errors of MASR reconstructions are reduced by 15% to 26% over bicubic interpolation method. Our codes are publicly available at https://github.com/MHDXing/MASR-for-Digital-Rock-Images.

show abstract

“…In recent years, learning-based SR methods [3] have been extensively studied, which use a learned co-occurrence to predict the correspondence between LR and HR patches. The learning algorithms including Markov network [4,5,6], neighbor embedding [7,8,9,10], dictionary learning [11,12,13,14], anchored neighborhood regression [16,15], random forests [17], and deep learning [18,19,20,21].…”

Section: Introductionmentioning

confidence: 99%

“…The k-nearest neighbor (k-NN) searching and the optimal reconstruction weights computing are performed in this unified feature space as well. Rahiman and George [9] propose learning-based approaches for single image super-resolution using sparse representation and neighbor embedding. Separate prediction models are trained for each cluster, and the model parameters are updated with each input image to adapt to input test image.…”

Section: Introductionmentioning

confidence: 99%

Image Super-Resolution Based on Sparse Coding with Multi-Class Dictionaries

Liao

Bai

Zhang

et al. 2019

cai

View full text Add to dashboard Cite

Sparse coding-based single image super-resolution has attracted much interest. In this paper, a super-resolution reconstruction algorithm based on sparse coding with multi-class dictionaries is put forward. We propose a novel method for image patch classification, using the phase congruency information. A subdictionary is learned from patches in each category. For a given image patch, the sub-dictionary that belongs to the same category is selected adaptively. Since the given patch has similar pattern with the selected sub-dictionary, it can be better represented. Finally, iterative back-projection is used to enforce global reconstruction constraint. Experiments demonstrate that our approach can produce comparable or even better super-resolution reconstruction results with some existing algorithms, in both subjective visual quality and numerical measures.

show abstract

Single image super resolution using neighbor embedding and statistical prediction model

Cited by 15 publications

References 12 publications

Remote Sensing Image Super-Resolution Using Texture Enhancing Generative Adversarial Network

Remote Sensing Image Super-Resolution Using Texture Enhancing Generative Adversarial Network

Multi Attention Neural Network for Digital Rock CT Images Super-Resolution

Image Super-Resolution Based on Sparse Coding with Multi-Class Dictionaries

Contact Info

Product

Resources

About