An Improvement of the VDSR Network for Single Image Super-Resolution by Truncation and Adjustment of the Learning Rate Parameters

Abstract A problem of single image super-resolution is considered, where the goal is to recover one high-resolution image from one low-resolution image. Whereas this problem has been successfully solved so far by the known VDSR network, such an approach still cannot give an overall beneficial effect compared to bicubic interpolation. This is so due to the fact that the image reconstruction quality has been estimated separately by three subjective factors. Moreover, the original VDSR network consisting of 20 convolutional layers is apparently not optimal by its depth. This is why here those factors are aggregated, and the network performance is deemed by a single estimator. Then the depth is tried to be decreased (truncation) along with adjusting the learning rate drop factor. Finally, a plausible improvement of the VDSR network is confirmed. The best truncated network, performing by almost 3.2 % better than bicubic interpolation, occupies less memory space and is about 1.44 times faster than the original VDSR network for images of a medium size.

Download Full-text

Gaussian Noised Single-Image Super Resolution Reconstruction

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.457-458.1032 ◽

2013 ◽

Vol 457-458 ◽

pp. 1032-1036

Author(s):

Feng Qing Qin ◽

Li Hong Zhu ◽

Li Lan Cao ◽

Wa Nan Yang

Keyword(s):

Gaussian Noise ◽

Signal To Noise Ratio ◽

Super Resolution ◽

Projection Algorithm ◽

Single Image ◽

Low Resolution ◽

Filtering Algorithm ◽

Resolution Image ◽

Image Super Resolution ◽

Single Image Super Resolution

A framework is proposed to reconstruct a super resolution image from a single low resolution image with Gaussian noise. The degrading processes of Gaussian blur, down-sampling, and Gaussian noise are all considered. For the low resolution image, the Gaussian noise is reduced through Wiener filtering algorithm. For the de-noised low resolution image, iterative back projection algorithm is used to reconstruct a super resolution image. Experiments show that de-noising plays an important part in single-image super resolution reconstruction. In the super reconstructed image, the Gaussian noise is reduced effectively and the peak signal to noise ratio (PSNR) is increased.

Download Full-text

Single-Image Super Resolution Reconstruction with Pepper and Salt Noise

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.427-429.1817 ◽

2013 ◽

Vol 427-429 ◽

pp. 1817-1821

Author(s):

Feng Qing Qin ◽

Li Hong Zhu ◽

Li Lan Cao ◽

Wa Nan Yang

Keyword(s):

Signal To Noise Ratio ◽

Super Resolution ◽

Projection Algorithm ◽

Single Image ◽

Low Resolution ◽

Resolution Image ◽

Imaging Model ◽

Resolution Imaging ◽

Image Super Resolution ◽

Single Image Super Resolution

In order to improve the resolution of single image with Pepper and Salt noise, a framework is proposed. In the low resolution imaging model, the Gaussian blur, down-sampling, as well as Pepper and Salt noise are considered. For the low resolution image, the Pepper and Salt noise is reduced through median filtering method. Super resolution reconstruction is performed on the de-noised low resolution image by iterative back projection algorithm. Experimental results show that the Pepper and Salt noise are removed effectively and the peak signal to noise ratio (PSNR) of the super resolution reconstructed image is improved.

Download Full-text

Deep Image Prior for Super Resolution of Noisy Image

Electronics ◽

10.3390/electronics10162014 ◽

2021 ◽

Vol 10 (16) ◽

pp. 2014

Author(s):

Sujy Han ◽

Tae Bok Lee ◽

Yong Seok Heo

Keyword(s):

Estimation Method ◽

Super Resolution ◽

Optimization Process ◽

Single Image ◽

Target Image ◽

Resolution Image ◽

Image Prior ◽

Deep Image ◽

Image Super Resolution ◽

Single Image Super Resolution

Single image super-resolution task aims to reconstruct a high-resolution image from a low-resolution image. Recently, it has been shown that by using deep image prior (DIP), a single neural network is sufficient to capture low-level image statistics using only a single image without data-driven training such that it can be used for various image restoration problems. However, super-resolution tasks are difficult to perform with DIP when the target image is noisy. The super-resolved image becomes noisy because the reconstruction loss of DIP does not consider the noise in the target image. Furthermore, when the target image contains noise, the optimization process of DIP becomes unstable and sensitive to noise. In this paper, we propose a noise-robust and stable framework based on DIP. To this end, we propose a noise-estimation method using the generative adversarial network (GAN) and self-supervision loss (SSL). We show that a generator of DIP can learn the distribution of noise in the target image with the proposed framework. Moreover, we argue that the optimization process of DIP is stabilized when the proposed self-supervision loss is incorporated. The experiments show that the proposed method quantitatively and qualitatively outperforms existing single image super-resolution methods for noisy images.

Download Full-text

Multi-scale Xception based depthwise separable convolution for single image super-resolution

PLoS ONE ◽

10.1371/journal.pone.0249278 ◽

2021 ◽

Vol 16 (8) ◽

pp. e0249278

Author(s):

Wazir Muhammad ◽

Supavadee Aramvith ◽

Takao Onoye

Keyword(s):

Research Work ◽

Super Resolution ◽

Single Image ◽

Low Resolution ◽

Significant Drop ◽

Great Ability ◽

Resolution Image ◽

Significant Performance ◽

Image Super Resolution ◽

Single Image Super Resolution

The main target of Single image super-resolution is to recover high-quality or high-resolution image from degraded version of low-quality or low-resolution image. Recently, deep learning-based approaches have achieved significant performance in image super-resolution tasks. However, existing approaches related with image super-resolution fail to use the features information of low-resolution images as well as do not recover the hierarchical features for the final reconstruction purpose. In this research work, we have proposed a new architecture inspired by ResNet and Xception networks, which enable a significant drop in the number of network parameters and improve the processing speed to obtain the SR results. We are compared our proposed algorithm with existing state-of-the-art algorithms and confirmed the great ability to construct HR images with fine, rich, and sharp texture details as well as edges. The experimental results validate that our proposed approach has robust performance compared to other popular techniques related to accuracy, speed, and visual quality.

Download Full-text

Single Image Super-Resolution viaL0Image Smoothing

Mathematical Problems in Engineering ◽

10.1155/2014/974509 ◽

2014 ◽

Vol 2014 ◽

pp. 1-8 ◽

Cited By ~ 1

Author(s):

Zhang Liu ◽

Qi Huang ◽

Jian Li ◽

Qi Wang

Keyword(s):

High Resolution ◽

Super Resolution ◽

Smoothing Method ◽

Single Image ◽

Low Resolution ◽

Resolution Image ◽

High Resolution Image ◽

Sharp Edges ◽

Image Super Resolution ◽

Single Image Super Resolution

We propose a single image super-resolution method based on aL0smoothing approach. We consider a low-resolution image as two parts: one is the smooth image generated by theL0smoothing method and the other is the error image between the low-resolution image and the smoothing image. We get an intermediate high-resolution image via a classical interpolation and then generate a high-resolution smoothing image with sharp edges by theL0smoothing method. For the error image, a learning-based super-resolution approach, keeping image details well, is employed to obtain a high-resolution error image. The resulting high-resolution image is the sum of the high-resolution smoothing image and the high-resolution error image. Experimental results show the effectiveness of the proposed method.

Download Full-text

Deep fractal residual network for fast and accurate single image super resolution

Neurocomputing ◽

10.1016/j.neucom.2019.09.093 ◽

2020 ◽

Vol 398 ◽

pp. 389-398 ◽

Cited By ~ 1

Author(s):

Yanghao Zhou ◽

Jianfeng Dong ◽

Yubin Yang

Keyword(s):

Super Resolution ◽

Single Image ◽

Residual Network ◽

Image Super Resolution ◽

Single Image Super Resolution

Download Full-text

Real-Time Environment Monitoring Using a Lightweight Image Super-Resolution Network

International Journal of Environmental Research and Public Health ◽

10.3390/ijerph18115890 ◽

2021 ◽

Vol 18 (11) ◽

pp. 5890

Author(s):

Qiang Yu ◽

Feiqiang Liu ◽

Long Xiao ◽

Zitao Liu ◽

Xiaomin Yang

Keyword(s):

Deep Learning ◽

Real Time ◽

Super Resolution ◽

Model Complexity ◽

Practical Application ◽

Single Image ◽

Feature Maps ◽

Benchmark Datasets ◽

Image Super Resolution ◽

Single Image Super Resolution

Deep-learning (DL)-based methods are of growing importance in the field of single image super-resolution (SISR). The practical application of these DL-based models is a remaining problem due to the requirement of heavy computation and huge storage resources. The powerful feature maps of hidden layers in convolutional neural networks (CNN) help the model learn useful information. However, there exists redundancy among feature maps, which can be further exploited. To address these issues, this paper proposes a lightweight efficient feature generating network (EFGN) for SISR by constructing the efficient feature generating block (EFGB). Specifically, the EFGB can conduct plain operations on the original features to produce more feature maps with parameters slightly increasing. With the help of these extra feature maps, the network can extract more useful information from low resolution (LR) images to reconstruct the desired high resolution (HR) images. Experiments conducted on the benchmark datasets demonstrate that the proposed EFGN can outperform other deep-learning based methods in most cases and possess relatively lower model complexity. Additionally, the running time measurement indicates the feasibility of real-time monitoring.

Download Full-text