Filters








5,679 Hits in 7.8 sec

Gradient-Guided and Multi-Scale Feature Network for Image Super-Resolution

Jian Chen, Detian Huang, Xiancheng Zhu, Feiyang Chen
2022 Applied Sciences  
To deal with this issue, we propose a gradient-guided and multi-scale feature network for image super-resolution (GFSR).  ...  Recently, deep-learning-based image super-resolution methods have made remarkable progress.  ...  [34] proposed a holistic attention network (HAN) for image super-resolution.  ... 
doi:10.3390/app12062935 fatcat:7n23dbbzj5bjddo2nzhrm4axnq

Image super-resolution algorithm based on RRDB model

Huan Li
2021 IEEE Access  
This work was financially supported in part by Research on the influence of the evolution of new generation network and information technology on Zhejiang media and its development trend (20NDYD022YB).  ...  INTRODUCTION Super-resolution reconstruction of a single image is a technique for recovering high-resolution images from lowresolution images.  ...  The existing super-resolution network models based on the attention mechanism usually use channel attention and spatial attention networks.  ... 
doi:10.1109/access.2021.3118444 fatcat:u26grayknrh2ti4ngi3ofyz6si

MESR: Multistage Enhancement Network for Image Super-Resolution

Detian Huang, Jian Chen
2022 IEEE Access  
To this end, a multi-stage enhancement image network for super-resolution (MESR) is proposed.  ...  The network consists of two stages, where the first stage is used to generate a coarse reconstructed image, and the second one is to refine the coarse image, which enhances the super-resolution performance  ...  To achieve more noteworthy refinement of the reconstructed images, Lai et al. [35] proposed a deep laplacian pyramid network for super-resolution (LapSRN).  ... 
doi:10.1109/access.2022.3176605 fatcat:hlbeh6hq2janppw37pidw7dmfa

Super-resolution reconstruction method of face image based on attention mechanism

Chenglin Yu, Hailong Pei
2021 IEEE Access  
In recent years, convolutional neural network in Single image super-resolution field show good results.  ...  Deep networks can establish complex mapping between low-resolution and high-resolution images, making the reconstructed images quality a great progress over traditional methods.  ...  INTRODUCTION Single Image Super-Resolution (SISR) is a low-level computer vision task.  ... 
doi:10.1109/access.2021.3070898 fatcat:lpopl3pp7nd2bbmkuse6gclghe

Hybrid Domain Attention Network for Efficient Super-Resolution

Qian Zhang, Linxia Feng, Hong Liang, Ying Yang
2022 Symmetry  
Specifically, the spatial self-attention module identifies important regions in the image, and the channel self-attention module adaptively emphasizes important channels.  ...  This paper proposes a symmetric CNN (HDANet), which is based on the Transformer's self-attention mechanism and uses symmetric convolution to capture the dependencies of image features in two dimensions  ...  [7] first applied CNN networks to single-image super-resolution reconstruction, proposing a three-layer convolutional neural network, SRCNN, and since then, more and more studies have tried to use CNN  ... 
doi:10.3390/sym14040697 fatcat:gxkypgoumnghpcjbjfuwqz6rce

Super-Resolution Network with Information Distillation and Multi-Scale Attention for Medical CT Image

Tianliu Zhao, Lei Hu, Yongmei Zhang, Jianying Fang
2021 Sensors  
In order to obtain high-quality medical CT images, we propose an information distillation and multi-scale attention network (IDMAN) for medical CT image super-resolution reconstruction.  ...  In a deep residual network, instead of only adding the convolution layer repeatedly, we introduce information distillation to make full use of the feature information.  ...  In this paper, our super-resolution reconstruction network for medical CT image references the residual network, attention mechanism and information distillation.  ... 
doi:10.3390/s21206870 pmid:34696083 pmcid:PMC8539557 fatcat:x64ockympndy3duyh3bzkzavcy

Adapting Image Super-Resolution State-Of-The-Arts and Learning Multi-Model Ensemble for Video Super-Resolution

Chao Li, Dongliang He, Xiao Liu, Yukang Ding, Shilei Wen
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
Recently, image super-resolution has been widely studied and achieved significant progress by leveraging the power of deep convolutional neural networks.  ...  In this paper, we investigate how to adapt state-ofthe-art methods of image super-resolution for video superresolution. The proposed adapting method is straightforward.  ...  Adapting Image Super-resolution State-of-thearts for Video Super-resolution We propose to learn deep spatial-temporal features for up-sampling video frames by adapting multiple state-ofthe-art image super-resolution  ... 
doi:10.1109/cvprw.2019.00255 dblp:conf/cvpr/LiHLDW19 fatcat:aoyu672zgvfv7eahsvu3a5kx2y

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

Jiayv Qin, Xianfang Sun, Yitong Yan, Longcun Jin, Xinyi Peng
2020 IEEE Access  
INDEX TERMS Channel-wise sub-network attention, convolutional neural networks, multi-resolution subnetworks, single image super-resolution.  ...  To overcome this problem, we propose a Multi-resolution space-Attended Residual Dense Network (MARDN) to separate lowfrequency and high-frequency information for reconstructing high-quality super-resolved  ...  Her current study interests are in single image super-resolution and deep learning.  ... 
doi:10.1109/access.2020.2976478 fatcat:itvsommeqvf35jclkmhodecrou

Multi-image Super Resolution of Remotely Sensed Images using Residual Feature Attention Deep Neural Networks [article]

Francesco Salvetti, Vittorio Mazzia, Aleem Khaliq, Marcello Chiaberge
2020 arXiv   pre-print
Extensive experimentation and evaluations against other available solutions, either for single or multi-image super-resolution, have demonstrated that the proposed deep learning-based solution can be considered  ...  state-of-the-art for Multi-Image Super-Resolution for remote sensing applications.  ...  There are two main methods used in Super-resolution: Single-image SR (SISR) and Multi-image SR (MISR). SISR employs a single image to reconstruct a HR version of it.  ... 
arXiv:2007.03107v2 fatcat:cdyx7nxxnnaxhczwoxggdsjdkm

Advances in deep learning for real-time image and video reconstruction and processing

Pourya Shamsolmoali, M. Emre Celebi, Ruili Wang
2020 Journal of Real-Time Image Processing  
Deep learning for image reconstruction and processing is a relatively new area.  ...  Reconstructing image is a central problem in many key applications including super-resolution imaging, X-ray tomography, ultrasound imaging, remote sensing, and magnetic resonance imaging.  ...  The paper "Optimised Highway Deep Learning Network for Fast Single Image Super-Resolution Reconstruction", aims at developing a novel model for single image super resolutions by using multi-scale connections  ... 
doi:10.1007/s11554-020-01026-2 fatcat:23jzdzkoxfdnrjfeew7bpwy7fm

Lightweight Feedback Convolution Neural Network for Remote Sensing Images Super-Resolution

Jin Wang, Yiming Wu, Liu Wang, Lei Wang, Osama Alfarraj, Amr Tolba
2021 IEEE Access  
INDEX TERMS Remote sensing, super-resolution, feedback mechanism, ghost module, attention mechanism.  ...  The super-resolution method can effectively restore the low-resolution image to the high-resolution image.  ...  CONCLUSION In this paper, we propose the feedback ghost residual dense network (FGRDN) of single-image super-resolution.  ... 
doi:10.1109/access.2021.3052946 fatcat:zndked7xizfrrjdxwe7fihthnm

Orientation-Aware Deep Neural Network for Real Image Super-Resolution

Chen Du, He Zewei, Sun Anshun, Yang Jiangxin, Cao Yanlong, Cao Yanpeng, Tang Siliang, Michael Ying Yang
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
Orientation-aware features extracted in different directions are adaptively combined through a channel-wise attention mechanism to generate more distinctive features for high-fidelity recovery of image  ...  In this paper, we proposed a novel orientation-aware deep neural network (OA-DNN) model, which incorporate a number of orientation feature extraction and channel attention modules (OAMs), to achieve good  ...  Introduction Single image super-Resolution (SISR) aims to recover corresponding high-resolution (HR) image from a single low-resolution (LR) image.  ... 
doi:10.1109/cvprw.2019.00246 dblp:conf/cvpr/ChenHSYCCTY19 fatcat:4g22xeovlfezlortcl46gjk2nm

Adapting Image Super-Resolution State-of-the-arts and Learning Multi-model Ensemble for Video Super-Resolution [article]

Chao Li, Dongliang He, Xiao Liu, Yukang Ding, Shilei Wen
2019 arXiv   pre-print
Recently, image super-resolution has been widely studied and achieved significant progress by leveraging the power of deep convolutional neural networks.  ...  In this paper, we investigate how to adapt state-of-the-art methods of image super-resolution for video super-resolution. The proposed adapting method is straightforward.  ...  Adapting Image Super-resolution State-of-thearts for Video Super-resolution We propose to learn deep spatial-temporal features for up-sampling video frames by adapting multiple state-ofthe-art image super-resolution  ... 
arXiv:1905.02462v1 fatcat:g3kannrxwbhojmbnouinrthht4

LSTNet: A Reference-Based Learning Spectral Transformer Network for Spectral Super-Resolution

Debao Yuan, Ling Wu, Huinan Jiang, Bingrui Zhang, Jian Li
2022 Sensors  
Spectral super-resolution (SSR) is a method that involves learning the relationship between a multispectral image (MSI) and an HSI, based on the overlap region, followed by reconstruction of the HSI by  ...  However, due to the limitations of the associated imaging systems and their sensors, such as the swath width and revisit period, hyperspectral imagery over a large coverage area cannot be acquired in a  ...  [32] proposed a deep residual single-image super-resolution network which uses a channel attention mechanism. Zhang et al.  ... 
doi:10.3390/s22051978 pmid:35271131 pmcid:PMC8914896 fatcat:sqgidsrk4bhqvfmbmlswgicrja

Channel-wise and Spatial Feature Modulation Network for Single Image Super-Resolution [article]

Yanting Hu, Jie Li, Yuanfei Huang, Xinbo Gao
2018 arXiv   pre-print
The performance of single image super-resolution has achieved significant improvement by utilizing deep convolutional neural networks (CNNs).  ...  To capture more informative features and maintain long-term information for image super-resolution, we propose a channel-wise and spatial feature modulation (CSFM) network in which a sequence of feature-modulation  ...  Abstract-The performance of single image super-resolution has achieved significant improvement by utilizing deep convolutional neural networks (CNNs).  ... 
arXiv:1809.11130v1 fatcat:r6f2nb5knvayjayzz33tboapqe
« Previous Showing results 1 — 15 out of 5,679 results