Variational probabilistic generative framework for single image super-resolution

Wang, Zhengjue; Chen, Bin; Zhang, Hao; Liu, Hongwei

doi:10.1016/j.sigpro.2018.10.004

Cited by 12 publications

(4 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The reconstruction quality is better than DR 2 -Net, but the reconstruction time is still longer than ReconNet. In the literature [25], the author proposed a variational probabilistic generative framework for single image super-resolution, which has some inspiration for the reconstruction of noisy images and improving the robustness of the algorithm. In literature [26], the author combines the ADMM method with the CSNet network, and the performance is also greatly improved.…”

Section: Deep Learning-based Cs Methodsmentioning

confidence: 99%

Fast bilateral complementary network for deep learning compressed sensing image reconstruction

Guo

Jiang

Chen

2022

IET Image Processing

View full text Add to dashboard Cite

Great progress has been made in deep learning image reconstruction, but there are still problems that need to be improved, such as the extraction of image texture details and the improvement of the overall contour quality of the image, and how to reduce the transmission cost is also the focus of research. This paper proposes a fast bilateral network suitable for both grayscale and color image reconstruction. In the compression network, bilinear interpolation, fully connected layer and convolutional neural network are selected for image compression. The reconstruction network is divided into two parts: the texture path and contour path, the former reconstructs the remaining texture details of the image, and the latter performs deep contour reconstruction. The bilateral complementary residual connection method transfers the texture information to the contour path and improves the contour quality, and the improvement of the contour quality can improve the learning of texture details. Through a large number of data tests, it shows that the network in this paper has achieved comparable or better results in terms of image reconstruction quality, time‐consuming and robustness against noise. It solves the problem of memory consumption for storing a large number of images, and also provides convenience for shortening space and time during image transmission.

show abstract

Section: Deep Learning-based Cs Methodsmentioning

confidence: 99%

Fast bilateral complementary network for deep learning compressed sensing image reconstruction

Guo

Jiang

Chen

2022

IET Image Processing

View full text Add to dashboard Cite

show abstract

“…Deep neural networks parameterize the relationship between latent space and original space. There have been many signs of progress along this direction in image processing, such as image denoising [38], image compression [52], and image super-resolution [47].…”

Section: Related Workmentioning

confidence: 99%

Unsupervised Deep Learning Meets Chan-Vese Model

Zheng¹,

Bao²,

Shi³

et al. 2022

Preprint

View full text Add to dashboard Cite

The Chan-Vese (CV) model is a classic region-based method in image segmentation. However, its piecewise constant assumption does not always hold for practical applications. Many improvements have been proposed but the issue is still far from well solved. In this work, we propose an unsupervised image segmentation approach that integrates the CV model with deep neural networks, which significantly improves the original CV model's segmentation accuracy. Our basic idea is to apply a deep neural network that maps the image into a latent space to alleviate the violation of the piecewise constant assumption in image space. We formulate this idea under the classic Bayesian framework by approximating the likelihood with an evidence lower bound (ELBO) term while keeping the prior term in the CV model. Thus, our model only needs the input image itself and does not require pre-training from external datasets. Moreover, we extend the idea to multi-phase case and dataset based unsupervised image segmentation. Extensive experiments validate the effectiveness of our model and show that the proposed method is noticeably better than other unsupervised segmentation approaches.

show abstract

“…The authors of SRNTT [36] focused on the information loss in LR images, and, proposed a reference-based SR approach for generating better texture details from reference images. A probabilistic generative framework, PGM, which offers the low computational cost and robustness to noise, is proposed in [37]. Reference [38] proposed G-GANISR exploiting the least square loss function instead of cross-entropy.…”

Section: A Super Resolution In Real World Imagingmentioning

confidence: 99%

Super Resolution of B-Mode Ultrasound Images With Deep Learning

Temiz

Bilge

2020

IEEE Access

View full text Add to dashboard Cite

Ultrasound offers a safe, non-invasive, and inexpensive way of imaging. However, due to its natural intrinsic imaging characteristics, it produces poor quality images with low resolution (LR) compared to other medical imaging modalities. Various image enhancement techniques have been extensively studied to overcome these shortcomings. Super-resolution (SR) is one of these methods, which endeavor to obtain high resolution (HR) images from LR images while enlarging them. Numerous studies have already utilized different SR techniques in various stages of ultrasound imaging (USI). Unlike other studies, which aimed at obtaining SR in the pre-processing phase or early stages of the post-processing phase of USI, we achieved SR on B-mode ultrasound images, which is the last stage of USI. We constructed a deep convolutional neural network (CNN) and trained it with a very large dataset of B-mode ultrasound images for the scale factors 2, 3, 4, and 8. We evaluated the performance of our proposed model quantitatively with eight image quality measures. The quantitative results revealed that our algorithm is much more successful than other methods at each magnification factor. Furthermore, we also verified that there is a statistically significant difference between our approach and others. Besides, qualitative analysis of the reconstructed images also confirms that it produces much better quality HR images than other methods in terms of the human visual system. INDEX TERMS Ultrasound, super-resolution, deep learning, convolutional neural network.

show abstract

Variational probabilistic generative framework for single image super-resolution

Cited by 12 publications

References 22 publications

Fast bilateral complementary network for deep learning compressed sensing image reconstruction

Fast bilateral complementary network for deep learning compressed sensing image reconstruction

Unsupervised Deep Learning Meets Chan-Vese Model

Super Resolution of B-Mode Ultrasound Images With Deep Learning

Contact Info

Product

Resources

About