Show simple item record

dc.contributor.authorSkorokhodov, Ivan
dc.date.accessioned2020-12-29T11:53:47Z
dc.date.available2020-12-29T11:53:47Z
dc.date.issued2020-12-24
dc.identifier.urihttp://hdl.handle.net/10754/666750
dc.description.abstractIn this work, we propose an approach to perform non-uniform image interpolation based on a Gaussian Mixture Model. Traditional image interpolation methods, like nearest neighbor, bilinear, Hamming, Lanczos, etc. assume that the coordinates you want to interpolate from, are positioned on a uniform grid. However, it is not always the case in practice and we develop an interpolation method that is able to generate an image from arbitrarily positioned pixel values. We do this by representing each known pixel as a 2D normal distribution and considering each output image pixel as a sample from the mixture of all the known ones. Apart from the ability to reconstruct an image from arbitrarily positioned set of pixels, this also allows us to differentiate through the interpolation procedure, which might be helpful for downstream applications. Our optimized CUDA kernel and the source code to reproduce the benchmarks is located at https://github.com/universome/non-uniform-interpolation.
dc.publisherarXiv
dc.relation.urlhttps://arxiv.org/pdf/2012.13257
dc.rightsArchived with thanks to arXiv
dc.titleInterpolating Points on a Non-Uniform Grid using a Mixture of Gaussians
dc.typePreprint
dc.contributor.departmentKAUST.
dc.eprint.versionPre-print
dc.identifier.arxivid2012.13257
kaust.personSkorokhodov, Ivan
dc.relation.issupplementedbygithub:universome/non-uniform-interpolation
refterms.dateFOA2020-12-29T11:54:18Z
display.relations<b>Is Supplemented By:</b><br/> <ul><li><i>[Software]</i> <br/> Title: universome/non-uniform-interpolation: Differentiable non-uniform interpolation: https://arxiv.org/abs/2012.13257. Publication Date: 2020-12-12. github: <a href="https://github.com/universome/non-uniform-interpolation" >universome/non-uniform-interpolation</a> Handle: <a href="http://hdl.handle.net/10754/667956" >10754/667956</a></a></li></ul>


Files in this item

Thumbnail
Name:
Preprintfile1.pdf
Size:
604.0Kb
Format:
PDF
Description:
Pre-print

This item appears in the following Collection(s)

Show simple item record