Filters








4,987 Hits in 6.0 sec

Triple Attention Mixed Link Network for Single Image Super Resolution [article]

Xi Cheng, Xiang Li, Jian Yang
2018 arXiv   pre-print
Single image super resolution is of great importance as a low-level computer vision task. Recent approaches with deep convolutional neural networks have achieved im-pressive performance.  ...  of attention mechanisms and 2) fu-sion of both powerful residual and dense connections (i.e., mixed link).  ...  U1713208 and 61472187, the 973 Program No. 2014CB349303, and Program for Changjiang Scholars.  ... 
arXiv:1810.03254v1 fatcat:ebttd7xqpfgqjdgeamzmul7nny

Triple-Attention Mixed-Link Network for Single-Image Super-Resolution

Xi Cheng, Xiang Li, Jian Yang
2019 Applied Sciences  
Single-image super-resolution is of great importance as a low-level computer-vision task. Recent approaches with deep convolutional neural networks have achieved impressive performance.  ...  ) of attention mechanisms and (2) fusion of both powerful residual and dense connections (i.e., mixed link).  ...  Abbreviations The following abbreviations are used in this manuscript: TAN Triple-attention mixed-link network CA Channel attention KA Kernel attention SA Spatial attention AE-MLB Attention-enhanced  ... 
doi:10.3390/app9152992 fatcat:azmvugentbaczcmnmgwgyifzga

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

Chenyang Duan, Nanfeng Xiao
2021 IET Computer Vision  
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.  ...  Stereo image pairs can effectively enhance the performance of super-resolution (SR) since both intra-view and cross-view information can be used.  ...  for Image Super-resolution.  ... 
doi:10.1049/cvi2.12063 fatcat:mghofhx75zdu3cawc5wxlw3ufy

A Single Frame and Multi-Frame Joint Network for 360-degree Panorama Video Super-Resolution [article]

Hongying Liu, Zhubo Ruan, Chaowei Fang, Peng Zhao, Fanhua Shang, Yuanyuan Liu, Lijun Wang
2020 arXiv   pre-print
In this paper, we propose a novel single frame and multi-frame joint network (SMFN) for recovering high-resolution spherical videos from low-resolution inputs.  ...  A mixed attention mechanism is devised to enhance the feature representation capability.  ...  Fig. 2 : The residual dense block in our reconstruction module. Conv Mixed attention: We adopts the attention mechanism to further enhance the representative ability of the proposed network.  ... 
arXiv:2008.10320v1 fatcat:un7amaq52zfvhasxyned24jvv4

Crop Leaf Disease Image Super-Resolution and Identification with Dual Attention and Topology Fusion Generative Adversarial Network

Qiang Dai, Xi Cheng, Yan Qiao, Youhua Zhang
2020 IEEE Access  
INDEX TERMS Crop leaf disease, attention, generative adversarial networks, super-resolution, identification. 55724 This work is licensed under a Creative Commons Attribution 4.0 License.  ...  This network can effectively transform unclear images into clear and high-resolution images.  ...  for image super-resolution tasks.  ... 
doi:10.1109/access.2020.2982055 fatcat:byx6nmhyb5hx3jj6vqwj4kvjtm

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

Pengxu Wei, Hannan Lu, Radu Timofte, Liang Lin, Wangmeng Zuo, Zhihong Pan, Baopu Li, Teng Xi, Yanwen Fan, Gang Zhang, Jingtuo Liu, Junyu Han (+64 others)
2020 arXiv   pre-print
The goal is to attract more attention to realistic image degradation for the SR task, which is much more complicated and challenging, and contributes to real-world image super-resolution applications.  ...  This paper introduces the real image Super-Resolution (SR) challenge that was part of the Advances in Image Manipulation (AIM) workshop, held in conjunction with ECCV 2020.  ...  The kailos team proposed RRBD Network with Attention mechanism using Wavelet loss for Single Image Super-Resolution.  ... 
arXiv:2009.12072v1 fatcat:7cwsjfhqa5cf7avfvdabpmxrda

Agricultural Pest Super-Resolution and Identification with Attention Enhanced Residual and Dense Fusion Generative and Adversarial Network

Qiang Dai, Xi Cheng, Yan Qiao, Youhua Zhang
2020 IEEE Access  
In this paper, we propose a generative adversarial network (GAN) with quadra-attention and residual and dense fusion mechanisms to transform low-resolution pest images.  ...  Additionally, the existing classification and segmentation methods are not satisfying for the identification of low-resolution images because they are pre-trained on the clear and high-resolution datasets  ...  To take good advantage of both residual and dense fusion mechanism, we carry out both residual and dense connections in a single layer.  ... 
doi:10.1109/access.2020.2991552 fatcat:26v3fenur5appffulqyixehvju

Real Image Super Resolution Via Heterogeneous Model Ensemble using GP-NAS [article]

Zhihong Pan, Baopu Li, Teng Xi, Yanwen Fan, Gang Zhang, Jingtuo Liu, Junyu Han, Errui Ding
2021 arXiv   pre-print
The proposed method won the first place in all three tracks of the AIM 2020 Real Image Super-Resolution Challenge.  ...  With advancement in deep neural network (DNN), recent state-of-the-art (SOTA) image superresolution (SR) methods have achieved impressive performance using deep residual network with dense skip connections  ...  Figure 1 : 1 The deep dense residual network architecture for image super resolution. Figure 2 : 2 The framework of the GP-NAS.  ... 
arXiv:2009.01371v2 fatcat:nwoeffzuzvhdhldltcwzpp2iwq

AIM 2019 Challenge on Real-World Image Super-Resolution: Methods and Results [article]

Andreas Lugmayr, Martin Danelljan, Radu Timofte, Manuel Fritsche, Shuhang Gu, Kuldeep Purohit, Praveen Kandula, Maitreya Suin, A N Rajagopalan, Nam Hyung Joon, Yu Seung Won, Guisik Kim, Dokyeong Kwon, Chih-Chung Hsu, Chia-Hsiang Lin (+6 others)
2019 arXiv   pre-print
In Track 2: Target Domain a set of high-quality images is also provided for training, that defines the output domain and desired quality of the super-resolved images.  ...  This paper reviews the AIM 2019 challenge on real world super-resolution. It focuses on the participating methods and final results.  ...  "Image super-resolution using very deep residual channel attention networks."  ... 
arXiv:1911.07783v2 fatcat:ik7qykxi35bp7lzvp2pf5o2iny

SRPRID: Pedestrian Re-identification based on Super-resolution Images

Zhen Qin, Wei He, Fuhu Deng, Meng Li, Meng Li, Yao Liu
2019 IEEE Access  
INDEX TERMS Person re-identification, super resolution, residual dense block, soft attention, hard attention, convolutional neural networks, video surveillance.  ...  Particularly, residual dense block (RDB) and Integrated Attention (InnAttn) block are merged to SRPRID.  ...  SR SUB-NETWORK The first sub-network is a residual dense network composed of multiple residual dense blocks. The input to the network are pedestrian images of different resolutions.  ... 
doi:10.1109/access.2019.2948260 fatcat:7apjdecsdbej3c63rncnvmomq4

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

Wazir Muhammad, Zuhaibuddin Bhutto, Arslan Ansari, Mudasar Latif Memon, Ramesh Kumar, Ayaz Hussain, Syed Ali Raza Shah, Imdadullah Thaheem, Shamshad Ali
2021 Electronics  
This paper proposes a multi-path network for SISR, known as multi-path deep CNN with residual inception network for 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.  ...  [66] introduced the concept of deep residual dense network architecture for single image super-resolution abbreviated as DRDN.  ... 
doi:10.3390/electronics10161979 fatcat:qf73qsxb3fafxfyopc3teyyf2u

MADNet: A Fast and Lightweight Network for Single-Image Super Resolution

Rushi Lan, Long Sun, Zhenbing Liu, Huimin Lu, Cheng Pang, Xiaonan Luo
2020 IEEE Transactions on Cybernetics  
Recently, deep convolutional neural networks (CNNs) have been successfully applied to the single-image super-resolution (SISR) task with great improvement in terms of both peak signal-to-noise ratio (PSNR  ...  Furthermore, we present a dual residual-path block (DRPB) that utilizes the hierarchical features from original low-resolution images.  ...  [26] introduced a multiscale residual network to exploit the image features to achieve a significant performance gain for image super resolution.  ... 
doi:10.1109/tcyb.2020.2970104 pmid:32149667 fatcat:unro5it6uzfznaugroxj7z3zya

Align-Filter & Learn Video Super Resolution using Deep learning (AFLVSR)

2019 International journal of recent technology and engineering  
The conventional techniques which are based on the image super-resolution are not suitable for multi-frame SR.  ...  During last decade, image super-resolution techniques have been introduced and adopted widely in various applications.  ...  Single image super-resolution has been studied widely and various techniques use the concept of single image SR for video SR [8] [9] .  ... 
doi:10.35940/ijrte.c1313.1183s319 fatcat:nq5xvsnpdjfgfnaknvxe5fg2uu

Multiple Optimizations-Based ESRFBN Super-Resolution Network Algorithm for MR Images

Huanyu Liu, Mingmei Shao, Jeng-Shyang Pan, Junbao Li
2021 Applied Sciences  
For multiple independent deep super-resolution networks, the output of a single network is integrated through an additional fusion layer, which broadens the width of the network, and can effectively improve  ...  In this paper, MR super-resolution based on the multiple optimizations-based Enhanced Super Resolution Feed Back Network (ESRFBN) is proposed.  ...  EDSR [18] : Enhanced Deep Residual Networks for Single Image Super-Resolution (EDSR) draws on the residual learning mechanism of the ResNet network.  ... 
doi:10.3390/app11178150 doaj:3f5007d845cd4b9baa0e42d5d85da920 fatcat:252jwqdmx5bihd25tejbnmghzy

Remote Sensing Image Super-Resolution via Residual Aggregation and Split Attentional Fusion Network

Long Chen, Hui Liu, Minhang Yang, Yurong Qian, Zhengqing Xiao, Xiwu Zhong
2021 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
To achieve high-quality super-resolution of remote sensing images, a residual aggregation and split attentional fusion network (RASAF) is proposed in this article.  ...  Second, to fully exploit multi-scale image information, a hierarchical loss function is used. Third, residual learning is used to reduce the difficulty of training in super-resolution tasks.  ...  Single image super-resolution (SISR) is the use of a low resolution (LR) image to generate a high resolution (HR) image using certain methods.  ... 
doi:10.1109/jstars.2021.3113658 fatcat:pfjvc3kojndndpgvdhhp7vqela
« Previous Showing results 1 — 15 out of 4,987 results