Filters








13,330 Hits in 3.0 sec

Enhanced Deep Residual Networks for Single Image Super-Resolution [article]

Bee Lim, Sanghyun Son, Heewon Kim, Seungjun Nah, Kyoung Mu Lee
2017 arXiv   pre-print
We also propose a new multi-scale deep super-resolution system (MDSR) and training method, which can reconstruct high-resolution images of different upscaling factors in a single model.  ...  In this paper, we develop an enhanced deep super-resolution network (EDSR) with performance exceeding those of current state-of-the-art SR methods.  ...  Introduction Image super-resolution (SR) problem, particularly single image super-resolution (SISR), has gained increasing research attention for decades.  ... 
arXiv:1707.02921v1 fatcat:64liy73w75fwfex5t24b5uwslm

Enhanced Deep Residual Networks for Single Image Super-Resolution

Bee Lim, Sanghyun Son, Heewon Kim, Seungjun Nah, Kyoung Mu Lee
2017 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
We also propose a new multi-scale deep super-resolution system (MDSR) and training method, which can reconstruct high-resolution images of different upscaling factors in a single model.  ...  In this paper, we develop an enhanced deep super-resolution network (EDSR) with performance exceeding those of current state-of-the-art SR methods.  ...  Introduction Image super-resolution (SR) problem, particularly single image super-resolution (SISR), has gained increasing research attention for decades.  ... 
doi:10.1109/cvprw.2017.151 dblp:conf/cvpr/LimSKNL17 fatcat:qrrmnvwbhjfjnesmmsgxfcjhke

Fixing Acceleration and Image Resolution Issues of Nuclear Magnetic Resonance

Krzysztof Malczewski
2020 Symmetry  
It has been proven that the proposed algorithm can enhance image spatial resolution and reduce motion artefacts and scan times.  ...  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  ...  network for image super-resolution [15] , Enhanced deep residual networks for single image super-resolution [14] and Image super-resolution using very deep residual channel attention networks [16]  ... 
doi:10.3390/sym12040681 fatcat:ymvqfkhxdvbwnp2veo5lijzk6a

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 novel loss function based on the weighted mean square error is proposed to emphasize on the super-resolution of the equatorial regions.  ...  Single Image Super-Resolution Single image super-resolution methods aim at learning the mapping between low-resolution images and high-resolution images, they take a single low-resolution image as input  ... 
arXiv:2008.10320v1 fatcat:un7amaq52zfvhasxyned24jvv4

Image Resolution Enhancement of Highly Compressively Sensed CT/PET Signals

Krzysztof Malczewski
2020 Algorithms  
as PET signal sensing with super-resolution (SR) image enhancement.  ...  This paper presents a super-resolution image enhancement algorithm designed for handling highly sensitively compressed hybrid CT/PET scanners raw data.  ...  I do not hold and I am not currently applying for any patents relating to the content of the manuscript. I do not have any other financial competing interests.  ... 
doi:10.3390/a13050129 fatcat:b2egb4selvfkhmdndbouowjbjm

Compnet: A New Scheme for Single Image Super Resolution Based on Deep Convolutional Neural Network

Alireza Esmaeilzehi, M. Omair Ahmad, M.N.S. Swamy
2018 IEEE Access  
In this paper, a novel residual deep network, called CompNet, is proposed for the single image super resolution problem without an excessive increase in the network complexity.  ...  INDEX TERMS Image super resolution, residual learning, deep learning.  ...  CONCLUSION In this work, a residual deep neural network architecture, called CompNet, has been proposed for the problem of single image super resolution.  ... 
doi:10.1109/access.2018.2874442 fatcat:wxfmykm43nctxfqvpdcdktm4ja

Towards super resolution in the compressed domain of learning-based image codecs

Evgeniy Upenik, Michela Testolina, Touradj Ebrahimi, Andrew G. Tescher, Touradj Ebrahimi
2021 Applications of Digital Image Processing XLIV  
Unlike the traditional approaches to image compression, learning-based codecs exploit deep neural networks for reducing dimensionality of the input at the stage where a linear transform would be typically  ...  In this paper, we explore the possibilities and propose an approach for super resolution that is applied in the latent space.  ...  •Enhanceddeep residual networks for single image super-resolution (EDSR)4by Lim et al. is a super resolution residual model, scoring first and second place at the NTIRE 2017 competition.  ... 
doi:10.1117/12.2597833 fatcat:xmp6ajpmdbb7to4pyn3bfd6eae

Image Super-Resolution Using Lightweight Multiscale Residual Dense Network

Shilin Li, Ming Zhao, Zhengyun Fang, Yafei Zhang, Hongjie Li, Wonho Jhe
2020 International Journal of Optics  
In order to solve the problem, we propose a multiscale residual dense network (MRDN) for image super-resolution. This network is constructed based on the residual dense network.  ...  Thus, it can better learn and fit the feature information of the original image and recover the satisfactory super-resolution image.  ...  Kim et al. a deeply-recursive convolutional network (DRCN) [14] and a very deep convolutional network (VDSR) [25] for image super-resolution.  ... 
doi:10.1155/2020/2852865 fatcat:gyu5u2kfg5hdhf2ff3ewvcupny

Adaptive deep residual network for single image super-resolution

Shuai Liu, Ruipeng Gang, Chenghua Li, Ruixia Song
2019 Computational Visual Media  
In the single image super-resolution (SISR) task, the convolutional neural network (CNN) extracts the features of the image through deeper layers, and has achieved impressive results.  ...  In this paper, we propose a single image super-resolution model based on Adaptive Deep Residual named as ADR-SR, which uses the Input Output Same Size (IOSS) structure, and releases the dependence of upsampling  ...  Conclusions In summary, we proposes a single image superresolution model named ADR-SR based on adaptive deep residual, which can be used for super-resolution task with the same size of input and output  ... 
doi:10.1007/s41095-019-0158-8 fatcat:x3lkbu6qzrhdzknsfcpbi25eju

Balanced Two-Stage Residual Networks for Image Super-Resolution

Yuchen Fan, Honghui Shi, Jiahui Yu, Ding Liu, Wei Han, Haichao Yu, Zhangyang Wang, Xinchao Wang, Thomas S. Huang
2017 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
In this paper, balanced two-stage residual networks (BT-SRN) are proposed for single image super-resolution.  ...  The deep residual design with constrained depth achieves the optimal balance between the accuracy and the speed for super-resolving images.  ...  networks for single image super-resolution.  ... 
doi:10.1109/cvprw.2017.154 dblp:conf/cvpr/FanSYLHYWWH17 fatcat:civz7z2ogvfbzn6cbrkfinjywa

Deep Convolutional Networks for Magnification of DICOM Brain Images

Kok Swee Sim, Fawaz Sammani
2019 International Journal of Innovative Computing, Information and Control  
In this paper, we propose a deep Convolutional Neural Network (CNN) for the enhancement of Digital Imaging and Communications in Medicine (DICOM) brain images.  ...  Convolutional neural networks have recently achieved great success in Single Image Super-Resolution (SISR). SISR is the action of reconstructing a high-quality image from a low-resolution one.  ...  The idea behind DenseNets is that Deep Convolutional Networks for Magnification of DICOM Brain Images. We propose a deep convolutional network for the purpose of single image super-resolution.  ... 
doi:10.24507/ijicic.15.02.725 fatcat:drnh7rlx25chtmx3iv5t7ls36u

Super-resolution reconstruction of a digital elevation model based on a deep residual network

Donglai Jiao, Dajiang Wang, Haiyang Lv, Yang Peng
2020 Open Geosciences  
The results show that DEM super-resolution based on a deep residual network is better than that obtained using a neural network with fewer convolutional layers, and the reconstructed result of the DEM  ...  based on a deep residual network is remarkably improved in terms of the peak signal to noise ratio and visual effect.  ...  Acknowledgments: We would like to thank Wei He for providing important feedback, suggestions and code contributions to the project.  ... 
doi:10.1515/geo-2020-0207 fatcat:3el2jsdu4veiznw3mhrycmsafa

A Deep Journey into Super-resolution: A survey [article]

Saeed Anwar, Salman Khan, Nick Barnes
2020 arXiv   pre-print
single image super-resolution.  ...  We introduce a taxonomy for deep-learning based super-resolution networks that groups existing methods into nine categories including linear, residual, multi-branch, recursive, progressive, attention-based  ...  Single-stage Residual Nets A single-stage design is composed of a single network; examples are shown next. • EDSR: The Enhanced Deep Super-Resolution (EDSR) [42] modifies the ResNet architecture [14  ... 
arXiv:1904.07523v3 fatcat:ovihxjadfja55hrytvhggj5c6q

ESRGAN+ : Further Improving Enhanced Super-Resolution Generative Adversarial Network [article]

Nathanaël Carraz Rakotonirina, Andry Rasoanaivo
2020 arXiv   pre-print
Enhanced Super-Resolution Generative Adversarial Network (ESRGAN) is a perceptual-driven approach for single image super resolution that is able to produce photorealistic images.  ...  Despite the visual quality of these generated images, there is still room for improvement. In this fashion, the model is extended to further improve the perceptual quality of the images.  ...  When only one low-resolution image is used, it is commonly called Single Image Super-Resolution (SISR).  ... 
arXiv:2001.08073v1 fatcat:d6klhqrmefbhteei3dgrqib3dm

Image Denoising and Super-Resolution using Residual Learning of Deep Convolutional Network [article]

Rohit Pardasani, Utkarsh Shreemali
2018 arXiv   pre-print
We propose and train a single deep learning network that we term as SuRDCNN (super-resolution and denoising convolutional neural network), to perform these two tasks simultaneously .  ...  Our model nearly replicates the architecture of existing state-of-the-art deep learning models for super-resolution and denoising.  ...  In residual learning the network learns a mapping from the input image to noise. In our work, we develop a single network capable of performing image super-resolution and denoising.  ... 
arXiv:1809.08229v1 fatcat:5x7givz4offy3latk34wyrfy5u
« Previous Showing results 1 — 15 out of 13,330 results