1,991 Hits in 8.9 sec

Super-resolution image reconstruction techniques: Trade-offs between the data-fidelity and regularization terms

Antigoni Panagiotopoulou, Vassilis Anastassopoulos
2012 Information Fusion  
This work considers stochastic regularized multi-frame SR image reconstruction from the data-fidelity point of view.  ...  In multi-frame Super-Resolution (SR) image reconstruction a single High-Resolution (HR) image is created from a sequence of Low-Resolution (LR) frames.  ...  Anastassopoulos, "Super-Resolution Image Reconstruction Techniques: Trade-Offs Between the Data-fidelity and Regularization Terms", Information Fusion, doi:10.1016 /j.inffus.2010 .11.005, 2010 J.  ... 
doi:10.1016/j.inffus.2010.11.005 fatcat:c2koxj3albfddmyfvflnaskrjq

Diffusion-Steered Super-Resolution Image Reconstruction [chapter]

Baraka J. Maiseli
2018 Colorimetry and Image Processing  
For decades, super-resolution has been a widely applied technique to improve the spatial resolution of an image without hardware modification.  ...  The goal is to establish an automatic interplay between TV and PM regularizers such that only their critical useful properties are extracted to well pose the super-resolution problem, and hence, to generate  ...  [18] , f = uη, where f is the corrupted image and λ is the fidelity parameter that balances the trade-off between u and f.  ... 
doi:10.5772/intechopen.71024 fatcat:yogrp3q4j5h35osvb3z3r7px4i

Adaptive Super-Resolution Image Reconstruction with Lorentzian Error Norm

S. Chandra Mohan
2017 Indian Journal of Science and Technology  
Super resolution reconstruction(SRR) is a computational technique to correct the degradation that the captured images normally suffer and this problem is ill-posed due to blur and noise present in the  ...  Objectives: To focus on an inverse problem of reconstructing a high resolution image from set of captured low resolution (LR) frames.  ...  Estimation of λ based on U-Curve Method The SRR problem depends on trade-off between the data fidelity term and prior term, and is totally controlled by the λ.  ... 
doi:10.17485/ijst/2017/v10i16/106780 fatcat:h7ubthev4bhkjjs62pcp4tedgy

POCS Based Super-Resolution Image Reconstruction Using an Adaptive Regularization Parameter [article]

S.S. Panda, M.S.R.S Prasad, G. Jena
2011 arXiv   pre-print
Super-resolution enables the extraction of this information by reconstructing a single image, at a high resolution than is present in any of the individual images.  ...  Super-resolution image restoration has been one of the most important research areas in recent years which goals to obtain a high resolution (HR) image from several low resolutions (LR) blurred, noisy,  ...  The projection of an arbitrary  Another important issue is the proper choice of   .   is regularization parameter that controls a trade-off between the fidelity to data (expressed by ||Y-HX|| 2  ... 
arXiv:1112.1484v1 fatcat:xxyatqceurazvmy43twtpcjqni

Multi-Frame Super-Resolution Reconstruction with Applications to Medical Imaging [article]

Thomas Köhler
2018 arXiv   pre-print
Super-resolution is a class of retrospective techniques that aims at high-resolution imagery by means of software.  ...  Multi-frame algorithms approach this task by fusing multiple low-resolution frames to reconstruct high-resolution images.  ...  R(x) ∝ − log p(x) denotes a regularization term with the regularization weight λ ≥ 0 to weight this term relative to the data fidelity.  ... 
arXiv:1812.09375v1 fatcat:k6gfmgb4o5cxvmaeoay4zfb5ly

SRR-Net: A Super-Resolution-Involved Reconstruction Method for High Resolution MR Imaging [article]

Wenqi Huang, Sen Jia, Ziwen Ke, Zhuo-Xu Cui, Jing Cheng, Yanjie Zhu, Dong Liang
2021 arXiv   pre-print
There are mainly two strategies dealing with the speed-resolution trade-off: (1) k-space undersampling with high-resolution acquisition, and (2) a pipeline of lower resolution image reconstruction and  ...  In this paper, we combine the idea of MR reconstruction and image super-resolution, and work on recovering HR images from low-resolution under-sampled k-space data directly.  ...  This work serves as a preliminary attempt to bridge the gap between MR image reconstruction and super-resolution.  ... 
arXiv:2104.05901v1 fatcat:h2ibk6ohfvg3zjyr4chstenytu

Image Super-Resolution Based on Alternative Registration, Blur Identification and Reconstruction [chapter]

Osama A. Omer
2012 Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering  
A solution to the problem of obtaining a high-resolution image from several low-resolution images is provided.  ...  The cost function is alternatively minimized with respect to registration parameters, blurring operators, and high resolution image.  ...  Adaptive Regularization and Step Size The regularization parameter, λ X, B, p , controls the trade-off between fidelity to the data and smoothness of the solution.  ... 
doi:10.1007/978-3-642-32573-1_8 fatcat:artbx3tba5gh7dfbcksdkgowqu

Single image super-resolution reconstruction based on genetic algorithm and regularization prior model

Yangyang Li, Yang Wang, Yaxiao Li, Licheng Jiao, Xiangrong Zhang, Rustam Stolkin
2016 Information Sciences  
Stolkin, R 2016, 'Single image super-resolution reconstruction based on genetic algorithm and regularization prior model ', Information Sciences, vol. 372,  ...  (7) , I is the identity matrix, and the first 2 l -norm term is the fidelity term; the second term is the non-local similarity regularization term, and  is the trade-off parameter to balance the non-local  ...  As one of the basic techniques in image reconstruction, super-resolution [21] reconstruction aims to derive a high resolution image from one or more low resolution image frames.  ... 
doi:10.1016/j.ins.2016.08.049 fatcat:kds4pxkixbhtnkqe2l4h5dp5bq

Guided Image Super-Resolution: A New Technique for Photogeometric Super-Resolution in Hybrid 3-D Range Imaging [chapter]

Florin C. Ghesu, Thomas Köhler, Sven Haase, Joachim Hornegger
2014 Lecture Notes in Computer Science  
Our guided super-resolution algorithm is formulated as joint maximum a-posteriori estimation to reconstruct high-resolution range and photometric data.  ...  In this paper, we augment multi-frame super-resolution with the concept of guided filtering for simultaneous upsampling of 3-D range data and complementary photometric information in hybrid range imaging  ...  and the support by the DFG under Grant No.  ... 
doi:10.1007/978-3-319-11752-2_18 fatcat:desajgi5xfggzhmwm72aluqyri

A MAP Algorithm to Super-Resolution Image Reconstruction

Huanfeng Shen, Pingxiang Li, Liangpei Zhang, Yindi Zhao
Third International Conference on Image and Graphics (ICIG'04)  
Super-resolution image reconstruction has been one of the most active research areas in recent years.  ...  In this paper, a new super-resolution algorithm is proposed to the problem of obtaining a high-resolution image from several low-resolution images that have been sub-sampled and displaced by different  ...  the balance between fidelity to the data and smoothness of the solution [11] .  ... 
doi:10.1109/icig.2004.8 dblp:conf/icig/ShenLZZ04 fatcat:nmfdoalx25gtvmtlghecwl25ny

A comparative study of various Deep Learning techniques for spatio-temporal Super-Resolution reconstruction of Forced Isotropic Turbulent flows [article]

T.S.Sachin Venkatesh, Rajat Srivastava, Pratyush Bhatt, Prince Tyagi, Raj Kumar Singh
2021 arXiv   pre-print
Super-resolution is an innovative technique that upscales the resolution of an image or a video and thus enables us to reconstruct high-fidelity images from low-resolution data.  ...  This study performs super-resolution analysis on turbulent flow fields spatially and temporally using various state-of-the-art machine learning techniques like ESPCN, ESRGAN and TecoGAN to reconstruct  ...  Raj Kumar Singh who provided expertise which greatly assisted us in the research and improved the paper significantly.  ... 
arXiv:2107.03361v1 fatcat:okltzsj6uzer3em2hcectjyxzq

Image and video quality improvement techniques for emerging applications

Volodymyr Ponomaryov, Thorsten Herfet, Vladimir Lukin, Bogdan Smolka, Vladimir Zlokolica
2012 EURASIP Journal on Advances in Signal Processing  
Another objective is evaluation of the trade-off between AL-FEC redundancy and video quality degradation for a given packet loss ratio.  ...  A post-processing synchronization between the original and the reconstructed streams has also been designed for improving the fidelity of the quality measures.  ...  Phillip Regalia, and the entire Publication Staff at Hindawi and BioMed for their dedication and hard work.  ... 
doi:10.1186/1687-6180-2012-33 fatcat:teei3npauzgjhnwauovkwlo5xa

Deep Learning for Efficient Reconstruction of High-Resolution Turbulent DNS Data [article]

Pranshu Pant, Amir Barati Farimani
2021 arXiv   pre-print
techniques used in image super-resolution.  ...  Our model efficiently reconstructs the high-fidelity DNS data from the LES like low-resolution solutions while yielding good reconstruction metrics.  ...  Herein lies the inherent trade-off between solution fidelity and computational complexity that CFD researchers and practitioners constantly grapple with.  ... 
arXiv:2010.11348v2 fatcat:may6m754qrcbto3nr3jgzg732i

Techniques for flexible image/video resolution conversion with heterogeneous terminals

Ming-sui Lee, Mei-yin Shen, C.-c. Kuo, Akio Yoneyama
2007 IEEE Communications Magazine  
The first term, which is the same as the traditional cost function, is the data fidelity penalty term which measures the similarity between the estimated HR frame and LR frames.  ...  The trade-off would be processing com-IFigure 3.  ... 
doi:10.1109/mcom.2007.284539 fatcat:73zhf6f2zfdorbp7stvgqlvbwa

Robust multi-frame super-resolution with adaptive norm choice and difference curvature based BTV regularization

Xiaohong Liu, Jiying Zhao
2017 2017 IEEE Global Conference on Signal and Information Processing (GlobalSIP)  
Multi-frame image super-resolution focuses on reconstructing a high-resolution image from a set of low-resolution images with high similarity.  ...  Since super-resolution is an ill-posted problem, regularization techniques are widely used to constrain the minimization function.  ...  K is the total number of LR images. Υ(X) is the regularization term. λ is the trade-off parameter between the fidelity term and the regularization term.  ... 
doi:10.1109/globalsip.2017.8308670 dblp:conf/globalsip/LiuZ17 fatcat:he6t4k4nzzerpfh4qpopma3mai
« Previous Showing results 1 — 15 out of 1,991 results