Optimization of Image B-spline Interpolation for GPU Architectures

• article
• demo
• archive

BibTeX info

Communicated by Pablo Arias
Demo edited by Thibaud Briand, Axel Davy

Abstract

Interpolation is a vital piece of many image processing pipelines. In this document we present how to optimize the implementation of image B-spline interpolation for GPU architectures. The implementation is based on the one proposed by Briand and Monasse in 2018 and works for orders up to 11. The two main optimizations consist in: (1) transposing the B-spline coefficients before the prefiltering of the rows and (2) dividing columns into subregions in order to use more threads. We assess the impact of the floating point precision and of using high B-spline orders.

Download

• full text manuscript: PDF low-res. (1.2MB) PDF (8.2MB) ^[?]
• source code: TAR/GZ SWHID info
  Software Heritage Archive @softwareversion{sw-ipol.2019.257, title = {{Optimization of Image B-spline Interpolation for GPU Architectures}}, author = {Thibaud Briand, Axel Davy}, date = {2019-04-11}, license = {BSD-3-Clause}, version = {1.0}, swhid = {swh:1:dir:c7784b2079abd60bf9dad027f2b1221287d0a9de;origin=https://doi.org/10.5201/ipol.2019.257;visit=swh:1:snp:9a82a3b286178c2ae158361d5b61cd7a64f151a0;anchor=swh:1:rel:862a4e9a4a956669e3104224d87f723cc24d5b4b}, related = {ipol.2019.257}, relatedtype = "Reference article: https://doi.org/10.5201/ipol.2019.257" } % the biblatex-software style extension is recommended for software bibitems
  Copy to clipboard

History

• Note from the editor: the manuscript of the article was modified on 2022-01-01 to include information about its editors. The original version of the manuscript is available here.