6,483 Hits in 7.5 sec

Densely Connected High Order Residual Network for Single Frame Image Super Resolution [article]

Yiwen Huang, Ming Qin
2018 arXiv   pre-print
Deep convolutional neural networks (DCNN) have been widely adopted for research on super resolution recently, however previous work focused mainly on stacking as many layers as possible in their model,  ...  in this paper, we present a new perspective regarding to image restoration problems that we can construct the neural network model reflecting the physical significance of the image restoration process  ...  Introduction Single image super resolution (SISR) has been one of the classic ill-posed problems of image restoration, it tries to reconstruct a high resolution (HR) image from a given low resolution (  ... 
arXiv:1804.05902v1 fatcat:pns5vcrjvjecfb7pov5tbvha74

Super resolution reconstruction algorithm of UAV image based on residual neural network

Xiaorong Zhang, Yueqi Ma
2021 IEEE Access  
In low resolution space, the dense residual network is used to obtain the complementary information of adjacent video frames, and then the optical flow of highresolution video frames is predicted through  ...  the pyramid structure, and then the low resolution video frames are transformed into high-resolution video frames through the sub-pixel convolution layer, The high-resolution video frame is compensated  ...  INTRODUCTION Super resolution reconstruction of a single image is a technique to recover high resolution image from low resolution image [1] [2] [3] .  ... 
doi:10.1109/access.2021.3114437 fatcat:7zvontrovrgtlkqpepb3hfqhbi

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.  ...  frames to generate the high-resolution frame.  ...  In order to overcome this problem, the super-resolution (SR) technique is considered as a promising solution to generate the high resolution (HR) image from a single image or sequence of LR images.  ... 
doi:10.35940/ijrte.c1313.1183s319 fatcat:nq5xvsnpdjfgfnaknvxe5fg2uu

Light Field Image Compression via CNN-Based EPI Super-Resolution and Decoder-Side Quality Enhancement

Jinbo Zhao, Ping An, Xinpeng Huang, Chao Yang, Liquan Shen
2019 IEEE Access  
We propose a multi-scale dense residual network (MSDRN) to implement both EPI super-resolution and quality enhancement.  ...  The low-resolution EPIs generated from the sparse SAIs are super-resolved by a CNN and the outputs, high-resolution EPIs, are used to rebuild the dense SAIs.  ...  The last network is for single image super-resolution, which is similar to our EPI superresolution network, so we compare the accuracy of their output high-resolution EPIs.  ... 
doi:10.1109/access.2019.2930644 fatcat:xjj63zrdrncltbhtmbvwp6hd2a

Optical Flow Super-Resolution Based on Image Guidence Using Convolutional Neural Network [article]

Liping Zhang, Zongqing Lu, Qingmin Liao
2018 arXiv   pre-print
With the motivation of various convolutional neural network(CNN) structures succeeded in single image super-resolution(SISR) task, an end-to-end convolutional neural network is proposed to reconstruct  ...  the high resolution(HR) optical flow field from initial LR optical flow with the guidence of the first frame used in optical flow estimation.  ...  in single blocks, multiple blocks are densely connected and residual connection is used on the whole.  ... 
arXiv:1809.00588v1 fatcat:7dmv3yx5hnfyjppib2wkxidldu

Deep Networks for Image and Video Super-Resolution [article]

Kuldeep Purohit, Srimanta Mandal, A. N. Rajagopalan
2022 arXiv   pre-print
To this end, we propose a deep architecture for single image super-resolution (SISR), which is built using efficient convolutional units we refer to as mixed-dense connection blocks (MDCB).  ...  We further employ our network for video super-resolution task, where our network learns to aggregate information from multiple frames and maintain spatio-temporal consistency.  ...  Our single-image SR network MDCN has been designed by effectively combining the residual and dense connections.  ... 
arXiv:2201.11996v1 fatcat:yjbmtfraozaddckgwpuqtmflmy

Fixing Acceleration and Image Resolution Issues of Nuclear Magnetic Resonance

Krzysztof Malczewski
2020 Symmetry  
A novel, rapid compressively-sensed magnetic resonance high-resolution image resolution algorithm is presented in this research paper.  ...  Due to highly challenging requirements for the accuracy of diagnostic images registration, the presented technique exploits image priors, deblurring, parallel imaging, and a deformable human body motion  ...  [45] , E: Enhanced deep residual networks for single image super-resolution [14] , F: Image super-resolution using very deep residual channel attention networks [16] , G: Residual dense network for  ... 
doi:10.3390/sym12040681 fatcat:ymvqfkhxdvbwnp2veo5lijzk6a

A Novel Dual Dense Connection Network for Video Super-resolution [article]

Guofang Li, Yonggui Zhu
2022 arXiv   pre-print
In this paper, we propose a novel dual dense connection network that can generate high-quality super-resolution (SR) results.  ...  Video super-resolution (VSR) refers to the reconstruction of high-resolution (HR) video from the corresponding low-resolution (LR) video. Recently, VSR has received increasing attention.  ...  Acknowledgement This paper is supported by the National Natural Science Foundation of China(No. 11571325) and the Fundamental Research Funds for the Central Universities(No. CUC2019 A002).  ... 
arXiv:2203.02723v1 fatcat:nbbj7b3chveg3bqtz5thonx4xi

MultiBoot Vsr: Multi-Stage Multi-Reference Bootstrapping for Video Super-Resolution

Ratheesh Kalarot, Fatih Porikli
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
We recurrently apply this network to reconstruct high-resolution frames and then reuse them as additional reference frames after reshuffling them into multiple low-resolution images.  ...  super-resolution.  ...  Rather than compensating for motion, [13, 8] operate on a stack of frames at the same time to generate different high-resolution images and then condense the results into a single image.  ... 
doi:10.1109/cvprw.2019.00258 dblp:conf/cvpr/KalarotP19 fatcat:44mzymchgzdxlo53s23tlczogq

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  
The super-resolution method can effectively restore the low-resolution image to the high-resolution image.  ...  For saving costs, we propose the feedback ghost residual dense network (FGRDN), which considers the feedback mechanism as the framework to attain lower features through high-level refining.  ...  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

Deformable Non-local Network For Video Super-Resolution [article]

Hua Wang, Dewei Su, Longcun Jin, Chuangchuang Liu
2019 arXiv   pre-print
The video super-resolution (VSR) task aims to restore a high-resolution video frame by using its corresponding low-resolution frame and multiple neighboring frames.  ...  To reconstruct the final high-quality HR video frames, we use residual in residual dense blocks to take full advantage of the hierarchical features.  ...  Related Work Single Image Super-resolution Dong et al.  ... 
arXiv:1909.10692v1 fatcat:kvmdpw3gpjhyvitfj7cjhc7e4e

D-SRGAN: DEM Super-Resolution with Generative Adversarial Networks

Bekir Z. Demiray, Muhammed Sit, Ibrahim Demir
2021 SN Computer Science  
The study also demonstrates that approaches from single image super-resolution can be applied for DEM super-resolution.  ...  In this paper, a GAN based model (D-SRGAN), inspired by single image super-resolution methods, is developed and evaluated to increase the resolution of DEMs.  ...  Super-resolution can be classified into two groups: multi-frame super-resolution and single image super-resolution (SISR) [29, 30] .  ... 
doi:10.1007/s42979-020-00442-2 fatcat:v55ng2neyrcoriveo25skhnqfe

Medical Video Super-Resolution Based on Asymmetric Back-Projection Network with Multilevel Error Feedback

Sheng Ren, Jianqi Li, Kehua Guo, Fangfang Li
2021 IEEE Access  
We construct a single-frame medical video super-resolution model as the benchmark model, combine the optical flow algorithm and multiframe fusion strategy to propose a medical video super-resolution method  ...  based on an asymmetric back-projection network with multilevel error feedback, and train high-quality and high-speed medical video super-resolution models.  ...  This article is extended from the Conference paper written by Sheng Ren in The 12th IEEE International Conference on Cyber, Physical and Social Computing (Towards Efficient Medical Video Super-Resolution  ... 
doi:10.1109/access.2021.3054433 fatcat:fyju5efvdbe5fd4q35i7m3d7vq

Development of Deep-Learning-Based Single-Molecule Localization Image Analysis

Yoonsuk Hyun, Doory Kim
2022 International Journal of Molecular Sciences  
However, the performance of single-molecule localization microscopy (SMLM) is significantly restricted by the image analysis method, as the final super-resolution image is reconstructed from identified  ...  Recent developments in super-resolution fluorescence microscopic techniques (SRM) have allowed for nanoscale imaging that greatly facilitates our understanding of nanostructures.  ...  In order to analyze super-resolution image data in high throughput, particularly for scanning a wide area of samples, the analysis needs to be accelerated.  ... 
doi:10.3390/ijms23136896 pmid:35805897 pmcid:PMC9266576 fatcat:rqds4g4bgbh7faupd55svwtnju

A Fuzzy rule- based Abandoned Object Detection using Image Fusion for Intelligent Video Surveillance Systems

Preetha K G
2021 Turkish Journal of Computer and Mathematics Education  
Video enhancement techniques like residual dense networks are adopted to improve the quality of the image before applying it to detect the abandoned objects and related humans.  ...  The related person is identified through reconstruction of the face through super-resolution techniques.  ...  The residual dense network contains residual dense blocks (RDB), which contains dense connected layers and local feature fusion.  ... 
doi:10.17762/turcomat.v12i3.1652 fatcat:d44iuasgqncfnlqfa5qgrstkim
« Previous Showing results 1 — 15 out of 6,483 results