Filters








28,758 Hits in 4.0 sec

Deep Back-Projection Networks for Single Image Super-resolution [article]

Muhammad Haris, Greg Shakhnarovich, Norimichi Ukita
2020 arXiv   pre-print
We propose Deep Back-Projection Networks (DBPN), the winner of two image super-resolution challenges (NTIRE2018 and PIRM2018), that exploit iterative up- and down-sampling layers.  ...  Previous feed-forward architectures of recently proposed deep super-resolution networks learn the features of low-resolution inputs and the non-linear mapping from those to a high-resolution output.  ...  CONCLUSION We have proposed Deep Back-Projection Networks for Single Image Super-resolution which is the winner of two single image SR challenge (NTIRE2018 and PIRM2018).  ... 
arXiv:1904.05677v2 fatcat:ozrsi7obcvcjzorbx55fxjwbfy

Deep Back-Projection Networks for Super-Resolution

Muhammad Haris, Greg Shakhnarovich, Norimichi Ukita
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition  
We propose Deep Back-Projection Networks (DBPN), that exploit iterative up-and downsampling layers, providing an error feedback mechanism for projection errors at each stage.  ...  The feed-forward architectures of recently proposed deep super-resolution networks learn representations of low-resolution inputs, and the non-linear mapping from those to high-resolution output.  ...  Conclusion We have proposed Deep Back-Projection Networks for Single Image Super-resolution.  ... 
doi:10.1109/cvpr.2018.00179 dblp:conf/cvpr/HarisSU18 fatcat:bo24jbi6sjanzmqn6qtstctt4y

Deep Back-Projection Networks For Super-Resolution [article]

Muhammad Haris, Greg Shakhnarovich, Norimichi Ukita
2018 arXiv   pre-print
We propose Deep Back-Projection Networks (DBPN), that exploit iterative up- and down-sampling layers, providing an error feedback mechanism for projection errors at each stage.  ...  The feed-forward architectures of recently proposed deep super-resolution networks learn representations of low-resolution inputs, and the non-linear mapping from those to high-resolution output.  ...  Conclusion We have proposed Deep Back-Projection Networks for Single Image Super-resolution.  ... 
arXiv:1803.02735v1 fatcat:vesoknrjtfgrboqwem6lco2eiq

Human Face Super-Resolution Based on Hybrid Algorithm

Jinfeng Xia, Zhizheng Yang, Fang Li, Yuanda Xu, Nan Ma, Chunxing Wang
2018 Advances in Molecular Imaging  
The iterative back-projection algorithm is combined with the convolutional neural network to create a new algorithm model.  ...  Aiming at the problems of image super-resolution algorithm with many convolutional neural networks, such as large parameters, large computational complexity and blurred image texture, we propose a new  ...  In this paper, the super-resolution algorithm based on convolution neural network is improved and combined with the iterative back-projection algorithm [10] , a new composite algorithm is proposed.  ... 
doi:10.4236/ami.2018.84004 fatcat:5uvsy7fxr5dejophfyj2lk4a5u

Image Super-Resolution via Attention based Back Projection Networks [article]

Zhi-Song Liu, Li-Wen Wang, Chu-Tak Li, Wan-Chi Siu, Yui-Lam Chan
2019 arXiv   pre-print
In this paper, we propose an Attention based Back Projection Network (ABPN) for image super-resolution.  ...  Deep learning based image Super-Resolution (SR) has shown rapid development due to its ability of big data digestion.  ...  Hence, there is a great potential for further study. Super-Resolution Deep Neural Networks. In the past few years, deep neural networks have shown remarkable ability on image SR.  ... 
arXiv:1910.04476v1 fatcat:7nyd6diyfnehbjmdntzlznujsm

Towards Efficient Video Detection Object Super-Resolution with Deep Fusion Network for Public Safety

Sheng Ren, Jianqi Li, Tianyi Tu, Yibo Peng, Jian Jiang, David Megías
2021 Security and Communication Networks  
Finally, we designed an asymmetric depth recursive back-projection network for super-resolution reconstruction.  ...  In this paper, we proposed an efficient video detection object super-resolution with a deep fusion network for public security.  ...  All the training and testing of the super-resolution model of the video detection object were completed on a high-performance server. is work was supported by the National Social Science Fund of China  ... 
doi:10.1155/2021/9999398 fatcat:uvsoflaltrdehgamgecbw7ex7q

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  
In this paper, we propose an advanced medical video super-resolution method based on an asymmetric back-projection network.  ...  based on an asymmetric back-projection network with multilevel error feedback, and train high-quality and high-speed medical video super-resolution models.  ...  based on Deep Back-Projection Networks).  ... 
doi:10.1109/access.2021.3054433 fatcat:fyju5efvdbe5fd4q35i7m3d7vq

Improved Super-resolution Reconstruction of Infrared Images Based on Deep Back-projection Networks

轩 刘, 晨晖 马, 仁浦 林, 力 张, 豪 张
2020 Infrared Technoiogy  
Deep back-projection networks have excellent performance in the super-resolution reconstruction of visual images.  ...  This paper explores the application of deep back-projection networks to the super-resolution reconstruction of infrared images.  ...  Back-Projection Stages Reconsturction 图 1 深度反投影网络结构图,主要包括初始化特征提取、反投影和重建 3 个部分 Fig.1 Architecture of the deep back-projection networks, it mainly consists of initial feature extraction, back-projection  ... 
doi:10.3724/sp.j.7102910263 fatcat:ppuncxmg2jczjbz5672ipzd5fy

Recurrent Back-Projection Network for Video Super-Resolution

Muhammad Haris, Gregory Shakhnarovich, Norimichi Ukita
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
These sources are combined in an iterative refinement framework inspired by the idea of back-projection in multiple-image super-resolution.  ...  We proposed a novel architecture for the problem of video super-resolution.  ...  Recently, Deep Back-Projection Networks (DBPN) [8] extended back-projection to Deep SISR under the assumption that only one LR image is given for the target image.  ... 
doi:10.1109/cvpr.2019.00402 dblp:conf/cvpr/HarisSU19 fatcat:lbvsqg3bhbgbxgxvejrimsq4hm

Reivew of Light Field Image Super-Resolution

Li Yu, Yunpeng Ma, Song Hong, Ke Chen
2022 Electronics  
In the early days of light field super-resolution research, many solutions for 2D image super-resolution, such as Gaussian models and sparse representations, were also used in light field super-resolution  ...  With the development of deep learning, light field image super-resolution solutions based on deep-learning techniques are becoming increasingly common and are gradually replacing traditional methods.  ...  Future research on light field super-resolution techniques should focus on the design of the network structure, it is worth considering how to adapt the network structure to the high-dimensional nature  ... 
doi:10.3390/electronics11121904 fatcat:kyecc2arf5da5mlsr556mvueo4

iSeeBetter: Spatio-temporal video super-resolution using recurrent generative back-projection networks [article]

Aman Chadha, John Britto, M. Mani Roja
2020 arXiv   pre-print
from the current and neighboring frames using the concept of recurrent back-projection networks as its generator.  ...  We present iSeeBetter, a novel GAN-based spatio-temporal approach to video super-resolution (VSR) that renders temporally consistent super-resolution videos. iSeeBetter extracts spatial and temporal information  ...  Acknowledgements The authors would like to thank Andrew Ng's lab at Stanford University for their guidance on this project.  ... 
arXiv:2006.11161v2 fatcat:uxl6vxkj5vgtrcgvfp22ipsbnm

Joint Back Projection and Residual Networks for Efficient Image Super-Resolution

Zhi-Song Liu, Wan-Chi Siu, Yui-Lam Chan
2018 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)  
We adopt the back projection blocks in our proposed network to provide the error correlated upand down-sampling process to replace simple deconvolution and pooling process for better estimation.  ...  Most deep networks focus on nonlinear mapping from low-resolution inputs to high-resolution outputs via residual learning without exploring the feature abstraction and analysis.  ...  Conclusion We have proposed a Hierarchical Back Projection Network for image Super-Resolution on different up-scaling factors.  ... 
doi:10.23919/apsipa.2018.8659476 dblp:conf/apsipa/LiuSC18 fatcat:z7ducofavvbypc6aqzks3elb2a

UNet-ESPC-Cascaded Super-Resolution Reconstruction in Spectral CT

Zhouxia Li, Xiaoni Wang, Lihui Wang, Wen Ji, Miaomiao Zhang, Yuemin Zhu, Feng Yang
2020 2020 15th IEEE International Conference on Signal Processing (ICSP)  
We propose to use deep learning methods for super-resolution reconstruction of spectral CT images.  ...  ground truth, by 11.6% and 5.66% with respect to respectively bilinear-interpolation-based reconstruction and iterative back projection methods.  ...  Douek for providing us the spectral CT data acquired in the framework of European Union Horizon 2020 grant No. 643694.  ... 
doi:10.1109/icsp48669.2020.9320976 fatcat:2hnrvlsnhfcilda6coajpnl6my

Multigrid Backprojection Super-Resolution and Deep Filter Visualization [article]

Pablo Navarrete Michelini, Hanwen Liu, Dan Zhu
2019 arXiv   pre-print
The network residuals are improved by Iterative Back-Projections (IBP) computed in the features of a convolutional network.  ...  We introduce a novel deep-learning architecture for image upscaling by large factors (e.g. 4x, 8x) based on examples of pristine high-resolution images.  ...  Thus, we aim to prove that convolutional networks are a natural and convenient choice for Super-Resolution (SR) tasks.  ... 
arXiv:1809.09326v3 fatcat:gen7pgo7l5h5dm2bv6ohau3xti

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.  ...  Deep Super Resolution (VDSR [10] ), Residual Dense Network (RDN) [11] , Super Resolution Generative Adversarial Network (SRGAN) [12] , Deep Back-projection Network (DBPN) [13] and Super Resolution  ... 
doi:10.3390/app11178150 doaj:3f5007d845cd4b9baa0e42d5d85da920 fatcat:252jwqdmx5bihd25tejbnmghzy
« Previous Showing results 1 — 15 out of 28,758 results