An image super-resolution deep learning network based on multi-level feature extraction module

Yang, Xin; Zhang, Yifan; Guo, Yingqing; Zhou, Dake

doi:10.1007/s11042-020-09958-4

Cited by 14 publications

(5 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…First, dense connection topological structure is to aggregate outputs of all dense unit to the end of dense block. In superresolution (SR) domain, deeper network helps to improve image reconstruction quality and introduce residual connection to avoid gradient disappearance, but deep network is computationally intensive and inefficient, Yang et al [ 59 ] used a new dense connection approach to extract low-resolution image features; model topology is to merge outputs of unit into the end of module and obtain deeper network and richer feature map by reducing the number of channels and network parameters; model was experimentally shown to be effective in SR with different magnifications. Mostefa et al [ 60 ] proposed DenseMultiOCM for extracting MRI image features in brain tumor segmentation, improved dense connection by connecting only unit output to final output of dense block, dense units in series to two 3 × 3 convolutions, and final unit used pooling and upsampling to extract half-scale features; experiments showed model segmentation results were improved.…”

Section: Development Of Densenetmentioning

confidence: 99%

Dense Convolutional Network and Its Application in Medical Image Analysis

Tao

XinYu

et al. 2022

BioMed Research International

View full text Add to dashboard Cite

Dense convolutional network (DenseNet) is a hot topic in deep learning research in recent years, which has good applications in medical image analysis. In this paper, DenseNet is summarized from the following aspects. First, the basic principle of DenseNet is introduced; second, the development of DenseNet is summarized and analyzed from five aspects: broaden DenseNet structure, lightweight DenseNet structure, dense unit, dense connection mode, and attention mechanism; finally, the application research of DenseNet in the field of medical image analysis is summarized from three aspects: pattern recognition, image segmentation, and object detection. The network structures of DenseNet are systematically summarized in this paper, which has certain positive significance for the research and development of DenseNet.

show abstract

Section: Development Of Densenetmentioning

confidence: 99%

Dense Convolutional Network and Its Application in Medical Image Analysis

Tao

XinYu

et al. 2022

BioMed Research International

View full text Add to dashboard Cite

show abstract

“…For the magnification factor ×S, f sub−conv5_×S () is the sub-pixel convolution with the convolution kernel size [5,5,3…”

Section: Skipmentioning

confidence: 99%

“…Suppose that the LR image with noise is LR N and the noise feature of LR image is LR NK , then NES can be expressed as 5 (1)…”

Section: The Cbdnet For Noise Cancellationmentioning

confidence: 99%

See 1 more Smart Citation

Remote sensing image super‐resolution based on convolutional blind denoising adaptive dense connection

Yang

Xie

Guo

et al. 2021

IET Image Processing

Self Cite

View full text Add to dashboard Cite

The current super-resolution (SR) deep network is mainly applied to the common image and pays little attention to the image with noise. The remote sensing image contains much noise, so that the SR reconstruction effect is not satisfactory. Therefore, a convolution blind denoising adaptive dense connection SR (CBD-ADCSR) network for the remote sensing image is proposed in this paper. The whole model is divided into a convolution blind denoising (CBD) network for denoising and an ADCSR network for reconstruction. Firstly, the components of the network are given in detail and are analysed. Secondly, a data set making method is designed combining motion blur, defocusing blur and Gaussian noise, which is used to generate low-resolution image data sets with complex degradation for the model training. Finally, through the detailed comparative experiment, it is proved that the reconstruction effect of the CBD-ADCSR model is better than that of the most state-of-the-art algorithms in objective criteria. In addition, compared with the original ADCSR network, CBD-ADCSR has a stronger ability for noise suppression.This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

show abstract

“…Currently, the mainstream of SISR research is the methods based on deep learning. It mainly includes SRCNN [13], SRGAN [14], STFGAN [15], LapSRN [16], SAN [17], RCAN [18], MAMSR [19][20][21], and so on, which has gradually achieved better subjective and objective performance.…”

Section: Introductionmentioning

confidence: 99%

A Robust Multiframe Image Super-Resolution Method in Variational Bayesian Framework

Min

Fan

2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Multiframe image super-resolution (MISR) combines complementary information of a set of low-resolution (LR) images to reconstruct a high-resolution (HR) one. In this study, we propose a robust and fully data-driven MISR method in the variational Bayesian framework. Different from the existing variational super-resolution (SR) methods, we use the l1 norm-based observation model, which takes the acquisition noise, outliers, and impulse noise into account. Furthermore, we have evaluated three typical image prior models, and the most appropriate one is chosen for our proposed method. The proposed method has the following advantages: (1) the HR image and all parameters are automatically estimated in an optimal stochastic sense; (2) the algorithm is robust to impulse noise and outliers. Extensive experiments with synthetic and real images demonstrate the advantages of the proposed method.

show abstract

An image super-resolution deep learning network based on multi-level feature extraction module

Cited by 14 publications

References 35 publications

Dense Convolutional Network and Its Application in Medical Image Analysis

Dense Convolutional Network and Its Application in Medical Image Analysis

Remote sensing image super‐resolution based on convolutional blind denoising adaptive dense connection

A Robust Multiframe Image Super-Resolution Method in Variational Bayesian Framework

Contact Info

Product

Resources

About