Filters








12,813 Hits in 3.8 sec

A Survey on Various Single Image Super Resolution Techniques
ENGLISH

A.Haza rathaiah
2013 International Journal of Innovative Research in Science, Engineering and Technology  
The SR image approaches reconstruct a single higher-resolution image from a set of given lower-resolution images . There is a basic need for digital images of higher resolutions and quality.  ...  Super resolution methods which is generate high-resolution (HR) image from one or more low resolution images and various image quality metrics reviewed as measure the original image and reconstructed image  ...  In short in first stage enhanced multiple images via single stage SR algorithm and in second stage combined them to produce a single high resolution SR image.  ... 
doi:10.15680/ijirset.2012.0102024 fatcat:t45xr2uapvcrdnzds7ldc37eta

Single Image Super-Resolution viaL0Image Smoothing

Zhang Liu, Qi Huang, Jian Li, Qi Wang
2014 Mathematical Problems in Engineering  
We propose a single image super-resolution method based on aL0smoothing approach.  ...  We get an intermediate high-resolution image via a classical interpolation and then generate a high-resolution smoothing image with sharp edges by theL0smoothing method.  ...  In particular, we address single image super-resolution in the paper.  ... 
doi:10.1155/2014/974509 fatcat:6zpupc62hreazjtphys47q6zm4

Example-Based Modeling of Facial Texture from Deficient Data

Arnaud Dessein, William A. P. Smith, Richard C. Wilson, Edwin R. Hancock
2015 2015 IEEE International Conference on Computer Vision (ICCV)  
Texture patches are selected by belief propagation so as to be consistent with neighbors and with observations in an appropriate image formation model.  ...  We further show applications to super-resolution where we substantially improve quality compared to a state-of-the-art algorithm, and to texture completion where we fill in missing regions and remove facial  ...  Hence, the majority of face-specific approaches to super-resolution work with a single image and are more accurately described as face hallucination (aka recogstruction as a neologism for reconstruction  ... 
doi:10.1109/iccv.2015.444 dblp:conf/iccv/DesseinSWH15 fatcat:fegnslxzyfewll3qc57zecteli

Super Resolution Technique Through Improved Neighbor Embedding
개선된 네이버 임베딩에 의한 초해상도 기법

Kyoung-Bae Eum
2014 Journal of Digital Contents Society  
For single image super resolution (SR), interpolation based and example based algorithms are extensively used. The interpolation algorithms have the strength of theoretical simplicity.  ...  Given a low resolution image, the pixel values in its high resolution version are estimated by the improved NE.  ...  Introduction Super resolution (SR) techniques estimate an image at higher resolution from its low resolution observations.  ... 
doi:10.9728/dcs.2014.15.6.737 fatcat:vy3dajmr25hmtoormrqwgd6qfm

Neighborhood regression for edge-preserving image super-resolution

Yanghao Li, Jiaying Liu, Wenhan Yang, Zongming Guo
2015 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)  
Rather than reconstructing the whole components in the image directly, we propose a novel edge-preserving super-resolution algorithm, which reconstructs low-and highfrequency components separately.  ...  There have been many proposed works on image superresolution via employing different priors or external databases to enhance HR results.  ...  Image Super-Resolution (SR) reconstruction is currently a popular research area in signal processing.  ... 
doi:10.1109/icassp.2015.7178160 dblp:conf/icassp/LiLYG15 fatcat:ok3dx7utdnf6nel5akkjyjzsni

Image super-resolution as sparse representation of raw image patches

Jianchao Yang, John Wright, Thomas Huang, Yi Ma
2008 2008 IEEE Conference on Computer Vision and Pattern Recognition  
This paper addresses the problem of generating a superresolution (SR) image from a single low-resolution input image. We approach this problem from the perspective of compressed sensing.  ...  We will demonstrate the effectiveness of sparsity as a prior for regularizing the otherwise ill-posed super-resolution problem.  ...  Super-resolution from Sparsity The single-image super-resolution problem asks: given a low-resolution image Y , recover a higher-resolution image X of the same scene.  ... 
doi:10.1109/cvpr.2008.4587647 dblp:conf/cvpr/YangWHM08 fatcat:crpeh7lwxvfgnjud3z2fbkfrwm

Joint Super-Resolution Using Only One Anisotropic Low-Resolution Image per q-Space Coordinate [chapter]

Vladimir Golkov, Jonathan I. Sperl, Marion I. Menzel, Tim Sprenger, Ek Tsoon Tan, Luca Marinelli, Christopher J. Hardy, Axel Haase, Daniel Cremers
2014 Mathematics and Visualization  
Recently, super-resolution methods for diffusion MRI capable of retrieving high-resolution diffusion-weighted images were proposed, yielding a resolution beyond the scanner hardware limitations.  ...  The introduced principles of joint super-resolution thus have the potential to further improve the performance of super-resolution methods.  ...  PSNR was 40:69 dB for low-resolution images, which could be improved to 41:33 dB for joint super-resolution images reconstructed from low-resolution images via the optimization problem (4), and 41:37 dB  ... 
doi:10.1007/978-3-319-11182-7_16 fatcat:jfjlm4jc4fbalbto7mpecdunvy

Advance Neighbor Embedding for Image Super Resolution

Dr. Ruikar Sachin D, Mr. Wadhavane Tushar D
2009 INTERNATIONAL JOURNAL OF COMPUTERS & TECHNOLOGY  
The assumption of the neighbor-embedding (NE) algorithm for single-image super-resolution Reconstruction is that the feature spaces are locally isometric of low-resolution and high-resolution Patches.  ...  This paper presents the Advance Neighbor embedding (ANE) method for image super resolution.  ...  Fig. 1 Illustration of neighbor embedding for Single image super-resolution ADVANCE NEIGHBOR EMBEDDING BASED SUPERRESOLUTION In this section, a MAP reconstruction framework for SR is discussed.  ... 
doi:10.24297/ijct.v8i2.3384 fatcat:hmsrk7oa45gh3o7jvdj5gafr3i

Single Image Super-Resolution - A Quantitative Comparison

Lisha P P, Jayasree V K
2015 International Journal of Engineering Research and  
Super-resolution (SR) techniques generates high resolution (HR) image from low resolution (LR) images.  ...  High resolution images improves the pictorial information for both human and automatic machine perception. This paper presents a comparison on well-known techniques of super resolution.  ...  Single image super-resolution technique generates HR image from single low resolution image. In multi image super-resolution, high resolution image is generated from multiple low resolution images.  ... 
doi:10.17577/ijertv4is050888 fatcat:65vgcn5xkzckxdbqbozfsqv6ma

Implicit LiDAR Network: LiDAR Super-Resolution via Interpolation Weight Prediction [article]

Youngsun Kwon, Minhyuk Sung, Sung-Eui Yoon
2022 arXiv   pre-print
Super-resolution of LiDAR range images is crucial to improving many downstream tasks such as object detection, recognition, and tracking.  ...  While deep learning has made a remarkable advances in super-resolution techniques, typical convolutional architectures limit upscaling factors to specific output resolutions in training.  ...  The LiDAR super-resolution networks reconstruct the upscaled range image having test resolution. We measure the mean absolute error (MAE) of all the pixels in the predicted 2-D range images.  ... 
arXiv:2203.06413v1 fatcat:ho4gdae7fvazta7s37ncvu324a

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

Hyperspectral Image Super-Resolution by Deep Spatial-Spectral Exploitation

Jing Hu, Minghua Zhao, Yunsong Li
2019 Remote Sensing  
The super-resolution (SR) technique aiming at enhancing the spatial resolution of the input image is a hot topic in computer vision.  ...  Second, the unselected bands are obtained via spectral correlation, yielding a coarse high-resolution (HR) HSI.  ...  PSNRs for different bands in the 8× reconstructed Scene02 HSIs via different single based methods.  ... 
doi:10.3390/rs11101229 fatcat:6vrwdhi6vfgrhdbonpm4nyqxdq

Video super-resolution via sparse combinations of key-frame patches in a compression context

Marco Bevilacqua, Aline Roumy, Christine Guillemot, Marie-Line Alberi Morel
2013 2013 Picture Coding Symposium (PCS)  
In this paper we present a super-resolution (SR) method for upscaling low-resolution (LR) video sequences, that relies on the presence of periodic high-resolution (HR) key frames, and validate it in the  ...  For a given LR intermediate frame, the HR details are retrieved patch-by-patch by taking sparse linear combinations of patches found in the neighbor key frames.  ...  CODING-BASED SUPER-RESOLUTION Example-based single-image SR (e.g. [1] , [5] , [4] ) aims at generating a HR upscaling of a LR input image, by means of a dictionary of training examples D.  ... 
doi:10.1109/pcs.2013.6737752 dblp:conf/pcs/BevilacquaRGA13 fatcat:aylzw3ddcng77illelv26zvidm

Local Consistency Constrained Adaptive Neighbor Embedding for Text Image Super-Resolution

Wei Fan, Jun Sun, Satoshi Naoi, Akihiro Minagawa, Yoshinobu Hotta
2012 2012 10th IAPR International Workshop on Document Analysis Systems  
First, we point out the non-local reconstruction problem in neighbor embedding based super-resolution by statistical analysis on an empirical data set.  ...  This paper proposes a robust single-image superresolution method for enlarging low quality camera captured text image. The contribution of this work is twofold.  ...  NEIGHBOR EMBEDDING A. The problem setting The single-image super-resolution problem that we want to solve can be formulated as follows.  ... 
doi:10.1109/das.2012.52 dblp:conf/das/FanSNMH12 fatcat:fhj3ka7mmvehhpajmgg2zwbaze

Joint Method of Interference Suppression and Super-Resolution for Chinese Characters Image with Interference

Bo Jiang, Wei Hu, Jian Liang, Shouxu Zhang, Xiaolei Ma, Yan Zhou, Jinping Niu, Xiaoxuan Chen
2018 Mathematical Problems in Engineering  
In the stage of image super-resolution, due to acquisition limitation of a large number of high-resolution Chinese characters images, we adopt neighbor embedding super-resolution method for its advantage  ...  Ultimately, a super-resolution method more suitable for Chinese characters image is proposed.  ...  Moreover, a DRRN (Deep Recursive Residual Network) for single image super-resolution is proposed by Ying Tai et al.  ... 
doi:10.1155/2018/4203121 fatcat:354mt23euvbcddjyjoboromizi
« Previous Showing results 1 — 15 out of 12,813 results