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 Enhanced Single Image Super Resolution Method Using Lightweight Multi-Scale Channel Dense Network

Sensors ◽  
2021 ◽  
Vol 21 (10) ◽  
pp. 3351
Author(s):  
Yooho Lee ◽  
Dongsan Jun ◽  
Byung-Gyu Kim ◽  
Hunjoo Lee
Keyword(s):  
Super Resolution ◽  
Perceptual Quality ◽  
Dense Network ◽  
Single Image ◽  
Resolution Method ◽  
Multi Scale ◽  
Training Images ◽  
Image Super Resolution ◽  
Single Image Super Resolution ◽  
Sr Method

Super resolution (SR) enables to generate a high-resolution (HR) image from one or more low-resolution (LR) images. Since a variety of CNN models have been recently studied in the areas of computer vision, these approaches have been combined with SR in order to provide higher image restoration. In this paper, we propose a lightweight CNN-based SR method, named multi-scale channel dense network (MCDN). In order to design the proposed network, we extracted the training images from the DIVerse 2K (DIV2K) dataset and investigated the trade-off between the SR accuracy and the network complexity. The experimental results show that the proposed method can significantly reduce the network complexity, such as the number of network parameters and total memory capacity, while maintaining slightly better or similar perceptual quality compared to the previous methods.

Generating High-Quality Air-Coupled Ultrasonic Images for Wooden Material Characterization by Single Image Super-Resolution

2019 ◽  
Vol 34 (03) ◽  
pp. 2054008
Author(s):  
Lujun Lin ◽  
Yiming Fang ◽  
Xiaochen Du ◽  
Zhu Zhou
Keyword(s):  
Image Quality ◽  
Super Resolution ◽  
Visual Assessment ◽  
Wood Products ◽  
Superior Performance ◽  
Single Image ◽  
High Quality ◽  
Practical Applications ◽  
Image Super Resolution ◽  
Single Image Super Resolution

As the practical applications in other fields, high-resolution images are usually expected to provide a more accurate assessment for the air-coupled ultrasonic (ACU) characterization of wooden materials. This paper investigated the feasibility of applying single image super-resolution (SISR) methods to recover high-quality ACU images from the raw observations that were constructed directly by the on-the-shelf ACU scanners. Four state-of-the-art SISR methods were applied to the low-resolution ACU images of wood products. The reconstructed images were evaluated by visual assessment and objective image quality metrics, including peak signal-to-noise-ratio and structural similarity. Both qualitative and quantitative evaluations indicated that the substantial improvement of image quality can be yielded. The results of the experiments demonstrated the superior performance and high reproducibility of the method for generating high-quality ACU images. Sparse coding based super-resolution and super-resolution convolutional neural network (SRCNN) significantly outperformed other algorithms. SRCNN has the potential to act as an effective tool to generate higher resolution ACU images due to its flexibility.

scholarly journals DEEP RESIDUAL LEARNING FOR SINGLE-IMAGE SUPER-RESOLUTION OF MULTI-SPECTRAL SATELLITE IMAGERY

2019 ◽  
Vol IV-2/W7 ◽  
pp. 189-196
Author(s):  
L. Wagner ◽  
L. Liebel ◽  
M. Körner
Keyword(s):  
Remote Sensing ◽  
Satellite Imagery ◽  
Network Architecture ◽  
Super Resolution ◽  
Superior Performance ◽  
Optical Remote Sensing ◽  
Single Image ◽  
Image Super Resolution ◽  
Single Image Super Resolution ◽  
The Individual

<p><strong>Abstract.</strong> Analyzing optical remote sensing imagery depends heavily on their spatial resolution. At the same time, this data is adversely affected by fixed sensor parameters and environmental influences. Methods for increasing the quality of such data and concomitantly optimizing its information content are, thus, in high demand. In particular, single-image super-resolution (SISR) approaches aim to achieve this goal solely by observing the individual images.</p><p>We propose to adapt a generic deep residual neural network architecture for SISR to deal with the special properties of remote sensing satellite imagery, especially taking into account the different spatial resolutions of individual Sentinel-2 bands, i.e., ground sampling distances of 20&amp;thinsp;m and 10&amp;thinsp;m. As a result, this method is able to increase the perceived resolution of the 20&amp;thinsp;m channels and mesh all spectral bands. Experimental evaluation and ablation studies on large datasets have shown superior performance compared to the state-of-the-art and that the model is not bound by its capacity.</p>

scholarly journals RBDN: Residual Bottleneck Dense Network for Image Super-Resolution

2021 ◽  
Author(s):  
Zeyu An ◽  
Junyuan Zhang ◽  
Ziyu Sheng ◽  
Xuanhe Er ◽  
Junjie Lv
Keyword(s):  
Network Architecture ◽  
Super Resolution ◽  
Dense Network ◽  
Single Image ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Network Building ◽  
Image Super Resolution ◽  
Feature Values ◽  
Single Image Super Resolution

Abstract Recent studies have shown that Super-Resolution Generative Adversarial Network (SRGAN) can significantly improve the quality of single-image super-resolution. However, the existing SRGAN approaches also have drawbacks, such as inadequate of features utilization, huge number of parameters and poor scalability. To further enhance the visual quality, we thoroughly study three key components of SRGAN: network architecture, adversarial loss and perceptual loss, and propose a DenseNet with Residual-in-Residual Bottleneck Block (RRBB) named as Residual Bottleneck Dense Network (RBDN) for single-image super-resolution. In particular, RBDN combines ResNet and DenseNet with different roles, in which ResNet refines feature values by addition and DenseNet memorizes feature values by concatenation. Specifically, the DenseNet adopts the Bottleneck structure to reduce the network parameters and improve the convergence rate. In addition, the proposed RRBB, as the basic network building unit, removes the batch normalization (BN) layer and employs the ELU function to reduce the opposite effects in the absence of BN. In this way, RBDN can enjoy the merits of the sufficient feature value refined by residual groups and the refined feature value memorized by dense connections, thus achieving better performance compared with most current residual blocks.

scholarly journals Image Restoration Based on Adaptive Dual-Domain Filtering

2018 ◽  
Vol 2018 ◽  
pp. 1-17
Author(s):  
Ruiqiang He ◽  
Xiangchu Feng ◽  
Chenping Zhao ◽  
Huazhu Chen ◽  
Xiaolong Zhu ◽  
...  
Keyword(s):  
Image Restoration ◽  
Learning Algorithm ◽  
Super Resolution ◽  
Image Deblurring ◽  
Superior Performance ◽  
Single Image ◽  
Denoising Method ◽  
Image Super Resolution ◽  
Single Image Super Resolution ◽  
Dual Domain

Image restoration is a long-standing problem in low-level computer vision. In this paper, we offer a simple but effective estimation paradigm for various image restoration problems. Specifically, we first propose a model-based Gaussian denoising method Adaptive Dual-Domain Filtering (ADDF) by learning the optimal confidence factors which are adjusted adaptively with Gaussian noise standard deviation. In addition, by generalizing this learning approach to Laplace noise, the learning algorithm of the optimum confidence factors in Laplace denoising is presented. Finally, the proposed ADDF is tactfully plugged into the method frameworks of off-the-shelf image deblurring and single image super-resolution (SISR). The approach, coining the name Plug-ADDF, achieves promising performance. Extensive experiments validate that the proposed ADDF for Gaussian and Laplace noise removals indeed results in visual and quantitative improvements over some existing state-of-the-art methods. Moreover, our Plug-ADDF for image deblurring and SISR also demonstrates superior performance objectively and subjectively.

scholarly journals Multi-Resolution Space-Attended Residual Dense Network for Single Image Super-Resolution

IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 40499-40511
Author(s):  
Jiayv Qin ◽  
Xianfang Sun ◽  
Yitong Yan ◽  
Longcun Jin ◽  
Xinyi Peng
Keyword(s):  
Super Resolution ◽  
Dense Network ◽  
Single Image ◽  
Image Super Resolution ◽  
Single Image Super Resolution

scholarly journals Memory‐ and time‐efficient dense network for single‐image super‐resolution

2021 ◽  
Author(s):  
Nasrin Imanpour ◽  
Ahmad R. Naghsh‐Nilchi ◽  
Amirhassan Monadjemi ◽  
Hossein Karshenas ◽  
Kamal Nasrollahi ◽  
...  
Keyword(s):  
Super Resolution ◽  
Dense Network ◽  
Single Image ◽  
Image Super Resolution ◽  
Single Image Super Resolution

scholarly journals Multi-Branch Deep Residual Network for Single Image Super-Resolution

Algorithms ◽  
2018 ◽  
Vol 11 (10) ◽  
pp. 144 ◽  
Author(s):  
Peng Liu ◽  
Ying Hong ◽  
Yan Liu
Keyword(s):  
Super Resolution ◽  
Superior Performance ◽  
Evaluation Function ◽  
Single Image ◽  
Residual Network ◽  
Perceptual Evaluation ◽  
Benchmark Datasets ◽  
Image Super Resolution ◽  
Single Image Super Resolution

Recently, algorithms based on the deep neural networks and residual networks have been applied for super-resolution and exhibited excellent performance. In this paper, a multi-branch deep residual network for single image super-resolution (MRSR) is proposed. In the network, we adopt a multi-branch network framework and further optimize the structure of residual network. By using residual blocks and filters reasonably, the model size is greatly expanded while the stable training is also guaranteed. Besides, a perceptual evaluation function, which contains three parts of loss, is proposed. The experiment results show that the evaluation function provides great support for the quality of reconstruction and the competitive performance. The proposed method mainly uses three steps of feature extraction, mapping, and reconstruction to complete the super-resolution reconstruction and shows superior performance than other state-of-the-art super-resolution methods on benchmark datasets.

Sign in / Sign up

Export Citation Format

Share Document