Single Image Super-Resolution Based on Deep Learning Features and Dictionary Model

Zhao, Liling; Sun, Quansen; Zhang, Zelin

doi:10.1109/access.2017.2736058

Cited by 30 publications

(19 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[24][25][26][27] Remarkable progress has been made with convolutional neural networks (CNNs), which can be used to reconstruct high-resolution images to photorealistic quality. 25,27 In this paper, we investigate whether super-resolution methods may be useful in condensed matter and statistical physics by allowing one to produce lattice configurations of larger sizes directly from those obtained for smaller systems. For concreteness, we focus on the classical Ising model in one and two dimensions.…”

Section: Introductionmentioning

confidence: 99%

Super-resolving the Ising model with convolutional neural networks

2019

View full text Add to dashboard Cite

Machine learning is becoming widely used in condensed matter physics. Inspired by the concept of image super-resolution, we propose a method to increase the size of lattice spin configurations using deep convolutional neural networks. Through supervised learning on Monte Carlo (MC) generated spin configurations, we train networks that invert real-space renormalization decimations. We demonstrate that super-resolution can reproduce thermodynamic observables that agree with MC calculations for the one and two-dimensional Ising model at various temperatures. We find that it is possible to predict thermodynamic quantities for lattice sizes larger than those used in training by extrapolating the parameters of the network. We use this method to compute the critical exponents of the 2D Ising model, finding good agreement with theory.

show abstract

Section: Introductionmentioning

confidence: 99%

Super-resolving the Ising model with convolutional neural networks

2019

View full text Add to dashboard Cite

show abstract

“…Our proposal contrasts with current deep learning approaches for microscopy, which involve post processing of previously acquired images. Mainly, these approaches increase the image quality by improving resolution 42 , denoising 43 or improving super-resolution image reconstruction 44 , without addressing the efficiency of imaging acquisition nor reducing number of samples or data storage. Other works also combined confocal or two-photon microscopy with machine learning algorithms in order to achieve software-based aberration corrections with adaptive optics 45 – 47 .…”

Section: Discussionmentioning

confidence: 99%

A machine learning approach for online automated optimization of super-resolution optical microscopy

Durand

Wiesner²,

Gardner

et al. 2018

Nat Commun

View full text Add to dashboard Cite

Traditional approaches for finding well-performing parameterizations of complex imaging systems, such as super-resolution microscopes rely on an extensive exploration phase over the illumination and acquisition settings, prior to the imaging task. This strategy suffers from several issues: it requires a large amount of parameter configurations to be evaluated, it leads to discrepancies between well-performing parameters in the exploration phase and imaging task, and it results in a waste of time and resources given that optimization and final imaging tasks are conducted separately. Here we show that a fully automated, machine learning-based system can conduct imaging parameter optimization toward a trade-off between several objectives, simultaneously to the imaging task. Its potential is highlighted on various imaging tasks, such as live-cell and multicolor imaging and multimodal optimization. This online optimization routine can be integrated to various imaging systems to increase accessibility, optimize performance and improve overall imaging quality.

show abstract

“…γ L yellowing (13) where µ , η and γ are the weights to configure layer preferences. w style is a weight that controls the style loss.…”

Section: F Final Loss Function Of Cpstmentioning

confidence: 99%

Convolutional Neural Network Style Transfer Towards Chinese Paintings

et al. 2019

View full text Add to dashboard Cite

Chinese painting is one of the most important cultural heritages. However, creating a Chinese painting usually requires specific skills, patience, and years of professional training. Moreover, most existing style transfer methods mainly focus on photograph or western painting, and there are intrinsic differences between Chinese and western paintings. To this end, we propose a novel algorithm of Chinese painting style transfer (CPST) towards transferring with unique ink and wash characteristics, which automatically generates Chinese paintings with machine learning technology. In this paper, firstly, comparing Chinese paintings with western works, we set up four key restrictions in the style transfer, i.e., with special considerations of typical ink and wash features, including brush stroke, space reservation, ink tone with diffusion and yellowing. In order to incorporate these restrictions into the transferring convolutional neural networks (CNN), we separate different layers of the CNN into layers of style and content, so as to faithfully reserve the style of the reference image. Secondly, as Chinese paintings can be divided into fine brushwork and freehand brushwork, to cope with diverse painting skills, we devise different strategies to transfer not only the ink tone but also the painting skills to the target images. Experiments show that taking the aesthetic characteristics of Chinese painting style as reference, our results are more visually satisfactory and successfully overcome spillovers. INDEX TERMS Chinese paintings, convolutional neural network, restrictions, style transfer.

show abstract

Single Image Super-Resolution Based on Deep Learning Features and Dictionary Model

Cited by 30 publications

References 28 publications

Super-resolving the Ising model with convolutional neural networks

Super-resolving the Ising model with convolutional neural networks

A machine learning approach for online automated optimization of super-resolution optical microscopy

Convolutional Neural Network Style Transfer Towards Chinese Paintings

Contact Info

Product

Resources

About