Filters








2,050 Hits in 4.4 sec

A polygon-based interpolation operator for super-resolution imaging [article]

Stéfan J. van der Walt, B. M. Herbst
2012 arXiv   pre-print
We then introduce an interpolation method based on polygonal pixel overlap, express it as a linear operator, and use it to improve reconstruction.  ...  We outline the super-resolution reconstruction problem posed as a maximization of probability.  ...  Both were collected by David Capel and is available for download from http://www.robots.ox.ac.uk/˜vgg/data.  ... 
arXiv:1210.3404v2 fatcat:kkxizsmgfjgenehbbqiyfs33h4

A Super-Resolution Image Reconstruction using Natural Neighbor Interpolation

Ramón Martín Rodríguez Dagnino
2015 Journal of Computacion y Sistemas  
In the second stage, the pixel values that match the high-resolution grid are interpolated using natural neighbor interpolation which is a weighted average interpolation method for scattered data, based  ...  A super-resolution image reconstruction algorithm using natural neighbor interpolation is proposed and its performance is evaluated.  ...  Conclusions In this paper we proposed a new super-resolution image reconstruction using natural neighbor interpolation.  ... 
doi:10.13053/cys-19-2-2068 fatcat:nx6pn5lkn5dnhpn426es5cflkq

Example-based super-resolution

W.T. Freeman, T.R. Jones, E.C. Pasztor
2002 IEEE Computer Graphics and Applications  
Example-based approaches Super-resolution relates to image interpolation-how should we interpolate between the digital samples of a photograph?  ...  We call methods for achieving high-resolution enlargements of pixel-based images super-resolution algorithms.  ...  Acknowledgments We thank Ted Adelson, Owen Carmichael, and John Haddon for helpful discussions.  ... 
doi:10.1109/38.988747 fatcat:55znw5lox5hgnoreqg7tl7djve

A physics-based approach to oversample multi-satellite, multi-species observations to a common grid

Kang Sun, Lei Zhu, Karen Cady-Pereira, Christopher Chan Miller, Kelly Chance, Lieven Clarisse, Pierre-François Coheur, Gonzalo Gonzalez Abad, Guanyu Huang, Xiong Liu, Martin Van Damme, Kai Yang (+1 others)
2018 Atmospheric Measurement Techniques Discussions  
An agile, physics-based oversampling approach is developed to represent each satellite observation as a sensitivity distribution on the ground, instead of a point or a polygon as assumed in previous approaches  ...  A generalized 2-D super Gaussian function is proposed to characterize the spatial response functions of both imaging grating spectrometers (e.g., OMI, OMPS, and TROPOMI) and scanning Fourier transform  ...  The target grid resolution for Level 3 data ranges from 0.25 • (∼25 km) for many global operational products to 0.01 • (∼1 km) for regional oversampling.  ... 
doi:10.5194/amt-2018-253 fatcat:q74mkvxvkvevxfy7lspys5p2ha

Radial Hermite operators for scattered point cloud data with normal vectors and applications to implicitizing polygon mesh surfaces for generalized CSG operations and smoothing

G.M. Nielson
2004 IEEE Visualization 2004  
The interpolation conditions above imply that the isosurface We describe a new technique for fitting scattered point cloud data.  ...  We take existing polygon mesh surfaces and use the present methods to construct implicit volume models for these surfaces.  ...  Acknowledgments Thanks to R Holmes, A. Huang, Y. Lu and S. Slyvester for their help.  ... 
doi:10.1109/visual.2004.87 dblp:conf/visualization/Nielson04 fatcat:az3utffjgbdyxbajbu3supamd4

Hallucinating Compressed Face Images

Chih-Yuan Yang, Sifei Liu, Ming-Hsuan Yang
2017 International Journal of Computer Vision  
For non-structural regions, an efficient generic super resolution algorithm is applied to generate high-resolution counterparts.  ...  For structural regions, landmarks are used to retrieve adequate high-resolution component exemplars in a large dataset based on the estimated head pose and illumination condition.  ...  For the mouth, we create the polygon based on 12 surrounding landmark points. For the nose, the polygon is created based on 5 landmark points at the bottom and 1 at the top.  ... 
doi:10.1007/s11263-017-1044-4 fatcat:tmlquez7vne27p54dvu4pbmlsu

An Impressionistic Cartographic Solution for Base Map Land Cover with Coarse Pixel Data

Paulo Raposo, Cynthia A Brewer, Kevin Sparks
2016 Cartographic Perspectives  
Additionally, raster data fine enough for a given map scale are not always available.  ...  Cartographic Solution for Base Map Land Cover with Coarse Pixel Data -Raposo et al.  ...  We do not attempt an interpolation or super-resolution in the uncertainty corridor for several reasons.  ... 
doi:10.14714/cp83.1351 fatcat:pxvfndyntbawjpgoteu4zyynhm

Multi-Spectral Multi-Image Super-Resolution of Sentinel-2 with Radiometric Consistency Losses and Its Effect on Building Delineation [article]

Muhammed Razzak, Gonzalo Mateo-Garcia, Luis Gómez-Chova, Yarin Gal, Freddie Kalaitzis
2021 arXiv   pre-print
We show that MISR is superior to single-image super-resolution and other baselines on a range of image fidelity metrics.  ...  To that end, we curate a multi-spectral multi-image super-resolution dataset, using PlanetScope imagery from the SpaceNet 7 challenge as the high resolution reference and multiple Sentinel-2 revisits of  ...  In addition, most of these models do not enforce physically-based consistency between the super-resolved image and its low-resolution counterpart [3] .  ... 
arXiv:2111.03231v1 fatcat:lvx2qreg7fdibhjjdl77dtimwi

A physics-based approach to oversample multi-satellite, multispecies observations to a common grid

Kang Sun, Lei Zhu, Karen Cady-Pereira, Christopher Chan Miller, Kelly Chance, Lieven Clarisse, Pierre-François Coheur, Gonzalo González Abad, Guanyu Huang, Xiong Liu, Martin Van Damme, Kai Yang (+1 others)
2018 Atmospheric Measurement Techniques  
An agile, physics-based oversampling approach is developed to represent each satellite observation as a sensitivity distribution on the ground, instead of a point or a polygon as assumed in previous methods  ...  A generalized 2-D super Gaussian function is proposed to characterize the spatial response functions of both imaging grating spectrometers (e.g., OMI, OMPS, and TROPOMI) and scanning Fourier transform  ...  Lieven Clarisse is a research associate with the Belgian F.R.S-FNRS and acknowledges the support. Edited by: Jun Wang Reviewed by: two anonymous referees  ... 
doi:10.5194/amt-11-6679-2018 fatcat:k7ac76iosndeta7nkj5zuw2mk4

Interactive volume on standard PC graphics hardware using multi-textures and multi-stage rasterization

C. Rezk-Salama, K. Engel, M. Bauer, G. Greiner, T. Ertl
2000 Proceedings of the ACM SIGGRAPH/EUROGRAPHICS workshop on Graphics hardware - HWWS '00  
In this paper we propose new rendering techniques that significantly improve both performance and image quality of the 2D-texture based approach.  ...  However the resulting images often contain visual artifacts caused by the lack of spatial interpolation.  ...  Acknowledgments We thank John Spitzer and NVidia for providing information and image material about the GeForce 256 hardware.  ... 
doi:10.1145/346876.348238 fatcat:e5wiwqcr7ffz5l5kgsgkntpatu

Super-resolution of periodic signals from short sequences of samples [article]

Marek W. Rupniewski
2020 arXiv   pre-print
For such a case, there exist some algorithms that allow for approximation of the sampled signal. However, these algorithms require bandlimitedness of the signal or noiseless samples.  ...  Reconstruction of undersampled periodic signals of unknown period is an important signal processing operation.  ...  The simplest super-resolution technique is based on the stroboscopic effect. To take advantage of this effect, one needs to get a precise estimate of period T .  ... 
arXiv:2010.11609v1 fatcat:swyh23ozdnc7tfbjsyffqscz7i

Making Low-Resolution Satellite Images Reborn: A Deep Learning Approach for Super-Resolution Building Extraction

Lixian Zhang, Runmin Dong, Shuai Yuan, Weijia Li, Juepeng Zheng, Haohuan Fu
2021 Remote Sensing  
In this paper, based on image super-resolution and segmentation techniques, we propose a two-stage framework (SRBuildingSeg) for achieving super-resolution (SR) building extraction using relatively low-resolution  ...  Existing methods for building extraction from remotely sensed images strongly rely on aerial or satellite-based images with very high resolution, which are usually limited by spatiotemporally accessibility  ...  Acknowledgments: We appreciate acdemic editor and the anonymous reviewers for their thoughtful and constructive suggestions and comments.  ... 
doi:10.3390/rs13152872 fatcat:vez7co4nuvcj3bpwvfwpojr3vy

Quadratic trigonometric B-spline for image interpolation using GA

Malik Zawwar Hussain, Samreen Abbas, Misbah Irshad, Yeng-Tseng Wang
2017 PLoS ONE  
In this article, a new quadratic trigonometric B-spline with control parameters is constructed to address the problems related to two dimensional digital image interpolation.  ...  The upshots show that the proposed scheme is better choice to deal with the problems associated to image interpolation.  ...  Acknowledgments Authors give special thanks to Signal and Image Processing Institute (SIPI), University of Southern California, Los Angeles, CA, for allowing use of their images freely.  ... 
doi:10.1371/journal.pone.0179721 pmid:28640906 pmcid:PMC5481006 fatcat:rym6tb67orexnnjocd3iereble

Distributed Acquisition and Image Super-Resolution Based on Continuous Moments from Samples

Loic Baboulaz, Pier Luigi Dragotti
2006 2006 International Conference on Image Processing  
Based on this, a new super-resolution algorithm was developed and showed good preliminary results.  ...  More importantly, we also show that those sampling schemes can be used for accurate registration of affine transformed and low-resolution images.  ...  A 2-D cubic interpolation followed by a restoration with a Wiener filter were then used to obtain a 2000x2000px super-resolved image (Figure 4(c) ).  ... 
doi:10.1109/icip.2006.312880 dblp:conf/icip/BaboulazD06 fatcat:w42f47xdine6vi3ydx6a5smowq

GNN-Surrogate: A Hierarchical and Adaptive Graph Neural Network for Parameter Space Exploration of Unstructured-Mesh Ocean Simulations [article]

Neng Shi, Jiayi Xu, Skylar W. Wurster, Hanqi Guo, Jonathan Woodring, Luke P. Van Roekel, Han-Wei Shen
2022 arXiv   pre-print
For efficient training, we generate hierarchical graphs and use adaptive resolutions.  ...  We propose GNN-Surrogate, a graph neural network-based surrogate model to explore the parameter space of ocean climate simulations.  ...  analyses, and the image-based method InSituNet [3] for comparison of image-based analyses.  ... 
arXiv:2202.08956v2 fatcat:clff73scivgy7oaiw6nsw4juwi
« Previous Showing results 1 — 15 out of 2,050 results