scholarly journals Wavelet-Integrated Deep Networks for Single Image Super-Resolution

Electronics ◽  
2019 ◽  
Vol 8 (5) ◽  
pp. 553 ◽  
Author(s):  
Faisal Sahito ◽  
Pan Zhiwen ◽  
Junaid Ahmed ◽  
Raheel Ahmed Memon
Keyword(s):  
Wavelet Transform ◽  
Similarity Index ◽  
Super Resolution ◽  
Training Data ◽  
Discrete Wavelet ◽  
Single Image ◽  
Data Set ◽  
Proposed Model ◽  
Image Super Resolution ◽  
Single Image Super Resolution

We propose a scale-invariant deep neural network model based on wavelets for single image super-resolution (SISR). The wavelet approximation images and their corresponding wavelet sub-bands across all predefined scale factors are combined to form a big training data set. Then, mappings are determined between the wavelet sub-band images and their corresponding approximation images. Finally, the gradient clipping process is used to boost the training speed of the algorithm. Furthermore, stationary wavelet transform (SWT) is used instead of a discrete wavelet transform (DWT), due to its up-scaling property. In this way, we can preserve more information about the images. In the proposed model, the high-resolution image is recovered with detailed features, due to redundancy (across the scale) property of wavelets. Experimental results show that the proposed model outperforms state-of-the algorithms in terms of peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM).

scholarly journals Single Image Super-Resolution: Depthwise Separable Convolution Super-Resolution Generative Adversarial Network

2020 ◽  
Vol 10 (1) ◽  
pp. 375 ◽  
Author(s):  
Zetao Jiang ◽  
Yongsong Huang ◽  
Lirui Hu
Keyword(s):  
Similarity Index ◽  
Super Resolution ◽  
Structural Similarity ◽  
Image Features ◽  
Single Image ◽  
Generative Adversarial Network ◽  
Visual Evaluation ◽  
Adversarial Network ◽  
Image Super Resolution ◽  
Single Image Super Resolution

The super-resolution generative adversarial network (SRGAN) is a seminal work that is capable of generating realistic textures during single image super-resolution. However, the hallucinated details are often accompanied by unpleasant artifacts. To further enhance the visual quality, we propose a deep learning method for single image super-resolution (SR). Our method directly learns an end-to-end mapping between the low/high-resolution images. The method is based on depthwise separable convolution super-resolution generative adversarial network (DSCSRGAN). A new depthwise separable convolution dense block (DSC Dense Block) was designed for the generator network, which improved the ability to represent and extract image features, while greatly reducing the total amount of parameters. For the discriminator network, the batch normalization (BN) layer was discarded, and the problem of artifacts was reduced. A frequency energy similarity loss function was designed to constrain the generator network to generate better super-resolution images. Experiments on several different datasets showed that the peak signal-to-noise ratio (PSNR) was improved by more than 3 dB, structural similarity index (SSIM) was increased by 16%, and the total parameter was reduced to 42.8% compared with the original model. Combining various objective indicators and subjective visual evaluation, the algorithm was shown to generate richer image details, clearer texture, and lower complexity.

scholarly journals Multi-Path Deep CNN with Residual Inception Network for Single Image Super-Resolution

Electronics ◽  
2021 ◽  
Vol 10 (16) ◽  
pp. 1979
Author(s):  
Wazir Muhammad ◽  
Zuhaibuddin Bhutto ◽  
Arslan Ansari ◽  
Mudasar Latif Memon ◽  
Ramesh Kumar ◽  
...  
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Computational Cost ◽  
Similarity Index ◽  
Super Resolution ◽  
Single Image ◽  
Index Matrix ◽  
Deep Cnn ◽  
Image Super Resolution ◽  
Single Image Super Resolution

Recent research on single-image super-resolution (SISR) using deep convolutional neural networks has made a breakthrough and achieved tremendous performance. Despite their significant progress, numerous convolutional neural networks (CNN) are limited in practical applications, owing to the requirement of the heavy computational cost of the model. This paper proposes a multi-path network for SISR, known as multi-path deep CNN with residual inception network for single image super-resolution. In detail, a residual/ResNet block with an Inception block supports the main framework of the entire network architecture. In addition, remove the batch normalization layer from the residual network (ResNet) block and max-pooling layer from the Inception block to further reduce the number of parameters to preventing the over-fitting problem during the training. Moreover, a conventional rectified linear unit (ReLU) is replaced with Leaky ReLU activation function to speed up the training process. Specifically, we propose a novel two upscale module, which adopts three paths to upscale the features by jointly using deconvolution and upsampling layers, instead of using single deconvolution layer or upsampling layer alone. The extensive experimental results on image super-resolution (SR) using five publicly available test datasets, which show that the proposed model not only attains the higher score of peak signal-to-noise ratio/structural similarity index matrix (PSNR/SSIM) but also enables faster and more efficient calculations against the existing image SR methods. For instance, we improved our method in terms of overall PSNR on the SET5 dataset with challenging upscale factor 8× as 1.88 dB over the baseline bicubic method and reduced computational cost in terms of number of parameters 62% by deeply-recursive convolutional neural network (DRCN) method.

scholarly journals Deep Residual Dense Network for Single Image Super-Resolution

Electronics ◽  
2021 ◽  
Vol 10 (5) ◽  
pp. 555
Author(s):  
Yogendra Rao Musunuri ◽  
Oh-Seol Kwon
Keyword(s):  
Super Resolution ◽  
Superior Performance ◽  
Perceptual Quality ◽  
Dense Network ◽  
Single Image ◽  
Proposed Model ◽  
Image Super Resolution ◽  
Perceptual Characteristics ◽  
Single Image Super Resolution ◽  
The Stability

In this paper, we propose a deep residual dense network (DRDN) for single image super- resolution. Based on human perceptual characteristics, the residual in residual dense block strategy (RRDB) is exploited to implement various depths in network architectures. The proposed model exhibits a simple sequential structure comprising residual and dense blocks with skip connections. It improves the stability and computational complexity of the network, as well as the perceptual quality. We adopt a perceptual metric to learn and assess the quality of the reconstructed images. The proposed model is trained with the Diverse2k dataset, and the performance is evaluated using standard datasets. The experimental results confirm that the proposed model exhibits superior performance, with better reconstruction results and perceptual quality than conventional methods.

scholarly journals Wavelet Domain Multidictionary Learning for Single Image Super-Resolution

2015 ◽  
Vol 2015 ◽  
pp. 1-12 ◽  
Author(s):  
Xiaomin Wu ◽  
Jiulun Fan ◽  
Jian Xu ◽  
Yanzi Wang
Keyword(s):  
Wavelet Transformation ◽  
Super Resolution ◽  
Principal Component ◽  
Discrete Wavelet ◽  
Single Image ◽  
Image Super Resolution ◽  
Single Image Super Resolution ◽  
Relationship Of ◽  
The Given ◽  
The Relationship

Image super-resolution (SR) aims at recovering the high-frequency (HF) details of a high-resolution (HR) image according to the given low-resolution (LR) image and some priors about natural images. Learning the relationship of the LR image and its corresponding HF details to guide the reconstruction of the HR image is needed. In order to alleviate the uncertainty in HF detail prediction, the HR and LR images are usually decomposed into 4 subbands after 1-level discrete wavelet transformation (DWT), including an approximation subband and three detail subbands. From our observation, we found the approximation subbands of the HR image and the corresponding bicubic interpolated image are very similar but the respective detail subbands are different. Therefore, an algorithm to learn 4 coupled principal component analysis (PCA) dictionaries to describe the relationship between the approximation subband and the detail subbands is proposed in this paper. Comparisons with various state-of-the-art methods by experiments showed that our proposed algorithm is superior to some related works.

scholarly journals A Sparse Analysis-Based Single Image Super-Resolution

Computers ◽  
2019 ◽  
Vol 8 (2) ◽  
pp. 41 ◽  
Author(s):  
Vahid Anari ◽  
Farbod Razzazi ◽  
Rasoul Amirfattahi
Keyword(s):  
Computational Complexity ◽  
High Resolution ◽  
Similarity Index ◽  
Super Resolution ◽  
Structural Similarity ◽  
Image Texture ◽  
Single Image ◽  
Low Resolution ◽  
Image Super Resolution ◽  
Single Image Super Resolution

In the current study, we were inspired by sparse analysis signal representation theory to propose a novel single-image super-resolution method termed “sparse analysis-based super resolution” (SASR). This study presents and demonstrates mapping between low and high resolution images using a coupled sparse analysis operator learning method to reconstruct high resolution (HR) images. We further show that the proposed method selects more informative high and low resolution (LR) learning patches based on image texture complexity to train high and low resolution operators more efficiently. The coupled high and low resolution operators are used for high resolution image reconstruction at a low computational complexity cost. The experimental results for quantitative criteria peak signal to noise ratio (PSNR), root mean square error (RMSE), structural similarity index (SSIM) and elapsed time, human observation as a qualitative measure, and computational complexity verify the improvements offered by the proposed SASR algorithm.

Sign in / Sign up

Export Citation Format

Share Document