Filters








9,410 Hits in 5.7 sec

Learning a Mixture of Deep Networks for Single Image Super-Resolution [article]

Ding Liu, Zhaowen Wang, Nasser Nasrabadi, Thomas Huang
2017 arXiv   pre-print
Prior arts have used either a mixture of simple regression models or a single non-linear neural network for this propose.  ...  Single image super-resolution (SR) is an ill-posed problem which aims to recover high-resolution (HR) images from their low-resolution (LR) observations.  ...  Conclusions In this paper, we propose to jointly learn a mixture of deep networks for single image super-resolution, each of which serves as a SR inference module to handle a certain class of image signals  ... 
arXiv:1701.00823v1 fatcat:7syinfyqbfdwlitfnh62tj3xp4

Advances in deep learning for real-time image and video reconstruction and processing

Pourya Shamsolmoali, M. Emre Celebi, Ruili Wang
2020 Journal of Real-Time Image Processing  
Deep learning for image reconstruction and processing is a relatively new area.  ...  Reconstructing image is a central problem in many key applications including super-resolution imaging, X-ray tomography, ultrasound imaging, remote sensing, and magnetic resonance imaging.  ...  The paper "Optimised Highway Deep Learning Network for Fast Single Image Super-Resolution Reconstruction", aims at developing a novel model for single image super resolutions by using multi-scale connections  ... 
doi:10.1007/s11554-020-01026-2 fatcat:23jzdzkoxfdnrjfeew7bpwy7fm

Advancing biological super-resolution microscopy through deep learning: a brief review [article]

Tianjie Yang, Yaoru Luo, Wei Ji, Ge Yang
2021 arXiv   pre-print
We focus primarily on how deep learning ad-vances reconstruction of super-resolution images. Related key technical challenges are discussed.  ...  In this brief Review, we survey recent advances in using deep learning to enhance performance of super-resolution microscopy.  ...  of China grant 91954201 under the major research program "Organellar interactomes for cellular homeostasis" and grant 31971289 to G.Y.), the Chinese Academy of Sciences (grant 292019000056), and the University  ... 
arXiv:2106.13064v1 fatcat:a7w7fzhqeneexgpvqs7rmqambi

Deep Convolutional Networks for Magnification of DICOM Brain Images

Kok Swee Sim, Fawaz Sammani
2019 International Journal of Innovative Computing, Information and Control  
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.  ...  In this paper, we propose a deep Convolutional Neural Network (CNN) for the enhancement of Digital Imaging and Communications in Medicine (DICOM) brain images.  ...  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

Lossless Image Compression through Super-Resolution [article]

Sheng Cao, Chao-Yuan Wu, Philipp Krähenbühl
2020 arXiv   pre-print
For lossless super-resolution, we predict the probability of a high-resolution image, conditioned on the low-resolution input, and use entropy coding to compress this super-resolution operator.  ...  We introduce a simple and efficient lossless image compression algorithm. We store a low resolution version of an image as raw pixels, followed by several iterations of lossless super-resolution.  ...  Qualitative Analysis Super-Resolution Distribution Visualization. Our network learns a distribution over possible super-resolutions.  ... 
arXiv:2004.02872v1 fatcat:ocwhfs5f55ht3o2dc3w3lfkcbe

CAESR: Conditional Autoencoder and Super-Resolution for Learned Spatial Scalability [article]

Charles Bonnineau, Wassim Hamidouche, Jean-François Travers, Naty Sidaty, Jean-Yves Aubié, Olivier Deforges
2022 arXiv   pre-print
Our approach relies on conditional coding that learns the optimal mixture of the source and the upscaled BL image, enabling better performance than residual coding.  ...  On the decoder side, a super-resolution (SR) module is used to recover high-resolution details and invert the conditional coding process.  ...  The models are trained over a total of 20 epochs with a learning rate of 10 −4 . We apply a learning rate decay with a gamma of 0.5 for the last 5 epochs to improve the convergence.  ... 
arXiv:2202.00416v1 fatcat:5ilwqyfulrbfvaavf3e7e2y3ja

Fast and Light-Weight Network for Single Frame Structured Illumination Microscopy Super-Resolution [article]

Xi Cheng, Jun Li, Qiang Dai, Zhenyong Fu, Jian Yang
2021 arXiv   pre-print
In this paper, we propose a single-frame structured illumination microscopy (SF-SIM) based on deep learning.  ...  We also design a bandpass attention module that makes our deep network more sensitive to the change of frequency and enhances the imaging quality.  ...  This work was supported by the National Science Fund of China under Grant No. U1713208, Program for Changjiang Scholars.  ... 
arXiv:2111.09103v1 fatcat:suzxrn2t4ragbbkbtut5272kam

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

2019 International journal of recent technology and engineering  
In this work, we address these issues and developed deep learning based novel architecture which performs feature alignment, filtering the image using deep learning and estimates the residual of low-resolution  ...  The conventional techniques which are based on the image super-resolution are not suitable for multi-frame SR.  ...  Recently, deep learning and convolutional neural network (CNN) based methods have emerged as a promising solution for single images SR.  ... 
doi:10.35940/ijrte.c1313.1183s319 fatcat:nq5xvsnpdjfgfnaknvxe5fg2uu

Reivew of Light Field Image Super-Resolution

Li Yu, Yunpeng Ma, Song Hong, Ke Chen
2022 Electronics  
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.  ...  However, as a kind of high-latitude data, light field images are difficult to acquire and store. Thus, the study of light field super-resolution is of great importance.  ...  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

Deep learning approaches for real-time image super-resolution

Pourya Shamsolmoali, M. Emre Celebi, Ruili Wang
2020 Neural computing & applications (Print)  
Generating a high-resolution (HR) image from its corresponding low-resolution (LR) input is referred to image super-resolution (SR).  ...  Recently, due to remarkable advances in deep learning, deep neural networks for SR have shown promising performance in several applications.  ...  Generating a high-resolution (HR) image from its corresponding low-resolution (LR) input is referred to image super-resolution (SR).  ... 
doi:10.1007/s00521-020-05176-z fatcat:gvmbzve6kvfmzfwumblipqzaji

Rethinking the Pipeline of Demosaicing, Denoising and Super-Resolution [article]

Guocheng Qian and Yuanhao Wang and Chao Dong and Jimmy S. Ren and Wolfgang Heidrich and Bernard Ghanem and Jinjin Gu
2021 arXiv   pre-print
Demosaicing (DM), denoising (DN), and super-resolution (SR) are core components in a digital image processing pipeline to overcome the three problems above, respectively.  ...  Our experiments show the benefit of the proposed PixelShift200 dataset for raw image processing.  ...  Super-resolution Single image super-resolution aims to recover the highresolution (HR) image from its low-resolution (LR) version.  ... 
arXiv:1905.02538v2 fatcat:k4gbl54aczce7jraesx4oqrnnu

GHM Wavelet Transform for Deep Image Super Resolution [article]

Ben Lowe, Hadi Salman, Justin Zhan
2022 arXiv   pre-print
Three large data sets are used for the experiments: DIV2K, a dataset of textures, and a dataset of satellite images.  ...  The GHM multi-level discrete wavelet transform is proposed as preprocessing for image super resolution with convolutional neural networks. Previous works perform analysis with the Haar wavelet only.  ...  A wavelet based deep neural network for super resolution was proposed by Tiantong Guo et al [3] .  ... 
arXiv:2204.07862v1 fatcat:g7yfzqurc5gbpma3bowvnruqiy

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.  ...  In this paper, a new single image super resolution scheme is developed through a mechanism of residual learning of a deep convolutional neural network.  ... 
doi:10.1109/access.2018.2874442 fatcat:wxfmykm43nctxfqvpdcdktm4ja

Hyperspectral Image Super-Resolution Based on Spatial Correlation-Regularized Unmixing Convolutional Neural Network

Xiaochen Lu, Dezheng Yang, Junping Zhang, Fengde Jia
2021 Remote Sensing  
Super-resolution (SR) technology has emerged as an effective tool for image analysis and interpretation.  ...  high-resolution HS image via the linear spectral mixture model.  ...  Gamba for providing the ROSIS data over Pavia; to the Hyperspectral Image Analysis group and the NSF Funded Center for Airborne Laser Mapping (NCALM) at the University of Houston; and to the IEEE GRSS  ... 
doi:10.3390/rs13204074 fatcat:hl7uaogyivevzlopjiu6kevp3a

Single-Image Super-Resolution Analysis in DCT Spectral Domain

Onur AYDIN, Ramazan Gökberk CİNBİŞ
2020 Balkan Journal of Electrical and Computer Engineering  
Super-Resolution Convolutional Neural Network (SR-CNN) [4] proposes one of the first deep learning architectures for single-image SR.  ...  Index Terms-Super resolution, deep learning, image process. Outline. In Section II, we provide a brief overview of deep learning based single-image SR.  ... 
doi:10.17694/bajece.714293 fatcat:ve2egj6vsngxxc3w2fccohyebe
« Previous Showing results 1 — 15 out of 9,410 results