8,074 Hits in 7.5 sec

Thermal Image Super-Resolution Using Second-Order Channel Attention with Varying Receptive Fields [article]

Nolan B. Gutierrez, William J. Beksi
2021 arXiv   pre-print
Our experimental results show an improvement over the state of the art when compared against competing thermal image super-resolution methods.  ...  For this purpose, we introduce a deep attention to varying receptive fields network (AVRFN).  ...  Introduction The purpose of single image super-resolution (SISR) restoration is to determine the mapping between a possibly degraded low-resolution (LR) image and its high-resolution (HR) counterpart.  ... 
arXiv:2108.00094v1 fatcat:vexnxncnqnbo3dbpib4op2yonu

Low-Light-Level Image Super-Resolution Reconstruction Based on a Multi-Scale Features Extraction Network

Bowen Wang, Yan Zou, Linfei Zhang, Yan Hu, Hao Yan, Chao Zuo, Qian Chen
2021 Photonics  
In order to perform data fusion and information extraction for low resolution (LR) images, the network extracts high-frequency detail information from different dimensions by combining the channel attention  ...  To solve these problems, we propose a multi-scale feature extraction (MSFE) network to realize pixel-super-resolved LLL imaging.  ...  For the most current super-resolution imaging methods, if the input image is a single channel gray image, the output image is also a single channel gray image.  ... 
doi:10.3390/photonics8080321 fatcat:vaikh25blrdsxbn5cdj4ysynom

A Matrix-in-matrix Neural Network for Image Super Resolution [article]

Hailong Ma and Xiangxiang Chu and Bo Zhang and Shaohua Wan and Bo Zhang
2019 arXiv   pre-print
In recent years, deep learning methods have achieved impressive results with higher peak signal-to-noise ratio in single image super-resolution (SISR) tasks by utilizing deeper layers.  ...  To address these issues, we propose a moderate-size SISR net work named matrixed channel attention network (MCAN) by constructing a matrix ensemble of multi-connected channel attention blocks (MCAB).  ...  With MIM enabled, PSNR is further promoted from 30.25 dB to 30.28 dB. Conclusion In this paper, we proposed an accurate and efficient network with matrixed channel attention for the SISR task.  ... 
arXiv:1903.07949v1 fatcat:3gsyj43v3jcehippnatp5lweie

Attention Mechanisms in CNN-Based Single Image Super-Resolution: A Brief Review and a New Perspective

Hongyu Zhu, Chao Xie, Yeqi Fei, Huanjie Tao
2021 Electronics  
With the advance of deep learning, the performance of single image super-resolution (SR) has been notably improved by convolution neural network (CNN)-based methods.  ...  Thus, this survey focuses on this topic and provides a review of these recently published works by grouping them into three major categories: channel attention, spatial attention, and non-local attention  ...  SRRAM Kim and Choi et al. [60] proposed the Residual Attention Module (RAM, shown in Figure 3b ) for Single Image Super-Resolution.  ... 
doi:10.3390/electronics10101187 fatcat:jsraiph2w5cgda6vhapo6qonkm

Image Super-Resolution Using Capsule Neural Networks

Jui-Ting Hsu, Chih-Hung Kuo, De-Wei Chen
2020 IEEE Access  
Convolutional neural networks (CNNs) have been widely applied in super-resolution (SR) and other image restoration tasks.  ...  In this paper, we develope two frameworks: the Capsule Image Restoration Neural Network (CIRNN) and the Capsule Attention and Reconstruction Neural Network (CARNN), to incorporate capsules into image SR  ...  Section II reviews CNN-based SR methods, capsule neural networks and attention networks. Section III presents the proposed image super-resolution frameworks.  ... 
doi:10.1109/access.2020.2964292 fatcat:x72g6eqtgrdb7d633kdtedkasy

From Local to Global: Efficient Dual Attention Mechanism for Single Image Super-Resolution

Pei Zhang, Edmund Y. Lam
2021 IEEE Access  
Convolutional neural networks (CNNs) have become a powerful approach for single image super-resolution (SISR).  ...  INDEX TERMS Attention mechanism, convolutional neural networks, super-resolution.  ...  INTRODUCTION Single image super-resolution (SISR) aims at restoring a high-resolution (HR) image from its low-resolution (LR) capture, which is an ill-posed inverse process due to multiple possible solutions  ... 
doi:10.1109/access.2021.3105726 fatcat:6shh2xixmvgwbby4t7hlsf7nxa

AIM 2020 Challenge on Efficient Super-Resolution: Methods and Results [article]

Kai Zhang, Martin Danelljan, Yawei Li, Radu Timofte, Jie Liu, Jie Tang, Gangshan Wu, Yu Zhu, Xiangyu He, Wenjie Xu, Chenghua Li, Cong Leng (+73 others)
2020 arXiv   pre-print
This paper reviews the AIM 2020 challenge on efficient single image super-resolution with focus on the proposed solutions and results.  ...  The track had 150 registered participants, and 25 teams submitted the final results. They gauge the state-of-the-art in efficient single image super-resolution.  ...  Acknowledgements We thank the AIM 2020 sponsors: HUAWEI, MediaTek, Google, NVIDIA, Qualcomm, and Computer Vision Lab (CVL) ETH Zurich. A Teams and affiliations  ... 
arXiv:2009.06943v1 fatcat:2s7k5wsgsjgo5flnqaby26cn64

Single Image Super-Resolution via a Holistic Attention Network [article]

Ben Niu, Weilei Wen, Wenqi Ren, Xiangde Zhang, Lianping Yang, Shuzhen Wang, Kaihao Zhang, Xiaochun Cao, Haifeng Shen
2020 arXiv   pre-print
Informative features play a crucial role in the single image super-resolution task. Channel attention has been demonstrated to be effective for preserving information-rich features in each layer.  ...  Extensive experiments demonstrate that the proposed HAN performs favorably against the state-of-the-art single image super-resolution approaches.  ...  Introduction Single image super-resolution (SISR) is an important task in computer vision and image processing.  ... 
arXiv:2008.08767v1 fatcat:nbtcquoy5vd5ligvpur6y4dqzi

Parallax‐based second‐order mixed attention for stereo image super‐resolution

Chenyang Duan, Nanfeng Xiao
2021 IET Computer Vision  
Stereo image pairs can effectively enhance the performance of super-resolution (SR) since both intra-view and cross-view information can be used.  ...  To address this issue, in this work, a parallax-based second-order mixed attention stereo SR network (PSMASSRnet) is proposed to integrate the cross-view information from a stereo image pair for SR.  ...  | Super-resolution | Single image super-resolution Single image SR methods, which are widely adopted by researchers, use a single LR image to recover a HR image.  ... 
doi:10.1049/cvi2.12063 fatcat:mghofhx75zdu3cawc5wxlw3ufy

Non-locally up-down convolutional attention network for remote sensing image super-resolution

Huan Wang, Qian Hu, Chengdong Wu, Jianning Chi, Xiaosheng Yu
2020 IEEE Access  
INDEX TERMS Single image super-resolution (SISR), channel-wise and space-wise attention mechanisms, deep learning, remote sensing image processing. H. Wang et al.: NLASR Sensing Image Super-Resolution  ...  Recently, single image super-resolution (SISR) has been widely applied in the field of remote sensing image processing and obtained remarkable performance.  ...  SINGLE IMAGE SUPER RESOLUTION DCNNs based SR algorithms consider SR as an imageto-image regression problem.  ... 
doi:10.1109/access.2020.3022882 fatcat:rwfs2hiydncm5cexfx46dhzq6u

DAQ: Channel-Wise Distribution-Aware Quantization for Deep Image Super-Resolution Networks [article]

Cheeun Hong, Heewon Kim, Sungyong Baik, Junghun Oh, Kyoung Mu Lee
2021 arXiv   pre-print
Quantizing deep convolutional neural networks for image super-resolution substantially reduces their computational costs.  ...  Our new method outperforms recent training-free and even training-based quantization methods to the state-of-the-art image super-resolution networks in ultra-low precision.  ...  Photo-realistic single image super-resolution using a Tang.  ... 
arXiv:2012.11230v2 fatcat:vx5j3lnhozfozkyndqaiqhr4iy

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
In this context, the presented research proposes a novel residual attention model (RAMS) that efficiently tackles the multi-image super-resolution task, simultaneously exploiting spatial and temporal correlations  ...  However, most of the works published in the literature have been focusing on the Single-Image Super-Resolution problem so far.  ...  , width, and channels of the single low-resolution images, respectively.  ... 
arXiv:2007.03107v2 fatcat:cdyx7nxxnnaxhczwoxggdsjdkm

Learning Frequency-aware Dynamic Network for Efficient Super-Resolution [article]

Wenbin Xie, Dehua Song, Chang Xu, Chunjing Xu, Hui Zhang, Yunhe Wang
2021 arXiv   pre-print
Deep learning based methods, especially convolutional neural networks (CNNs) have been successfully applied in the field of single image super-resolution (SISR).  ...  Since pixels or image patches belong to low-frequency areas contain relatively few textural details, this dynamic network will not affect the quality of resulting super-resolution images.  ...  Conclusion In this paper, a novel frequency-aware dynamic network (FADN) is proposed for efficient single image super resolution, which assigns cheap operations to low-frequency regions and vice visa.  ... 
arXiv:2103.08357v2 fatcat:vnwyt7rdvnbk7gvf4zm7nnleou

Lightweight Multi-Scale Asymmetric Attention Network for Image Super-Resolution

Min Zhang, Huibin Wang, Zhen Zhang, Zhe Chen, Jie Shen
2021 Micromachines  
Recently, with the development of convolutional neural networks, single-image super-resolution (SISR) has achieved better performance.  ...  However, the practical application of image super-resolution is limited by a large number of parameters and calculations.  ...  Introduction Image super-resolution (SR) is the process of recovering a high-resolution (HR) image from a given low-resolution (LR) image.  ... 
doi:10.3390/mi13010054 pmid:35056219 pmcid:PMC8778112 fatcat:pkmz2jh57fg27bsg5v5e3ebndy

Single Image Super-Resolution via Similarity between Spatially Scattered Features

Jeonghyo Ha, Yungsoo Kim, Junmo Kim
2020 IEEE Access  
ACKNOWLEDGMENT Jeonghyo Ha and Yungsoo Kim contributed equally to this work.  ...  INTRODUCTION Single image super-resolution (SISR) is a low-level vision problem that aims to infer a high-resolution (HR) image with high-frequency details from a low-resolution (LR) query image.  ...  In this paper, we propose a single image super-resolution via similarity between spatially scattered features which utilize non-local attention networks for the similarity information.  ... 
doi:10.1109/access.2020.3011566 fatcat:okpquhfrxzhihbgwys6d74hcqm
« Previous Showing results 1 — 15 out of 8,074 results