ML Anthology

N-Dimensional Probablility Density Function Transfer and Its Application to Colour Transfer

François Pitié, Anil C. Kokaram, Rozenn Dahyot
ICCV 2005 pp. 1434-1439
doi:10.1109/ICCV.2005.166 /iccv/2005/pitie2005iccv-n/

Abstract

This article proposes an original method to estimate a continuous transformation that maps one N-dimensional distribution to another. The method is iterative, non-linear, and is shown to converge. Only 1D marginal distribution is used in the estimation process, hence involving low computation costs. As an illustration this mapping is applied to color transfer between two images of different contents. The paper also serves as a central focal point for collecting together the research activity in this area and relating it to the important problem of automated color grading

PDF ICCV Semantic Scholar

Cite

Text

Pitié et al. "N-Dimensional Probablility Density Function Transfer and Its Application to Colour Transfer." IEEE/CVF International Conference on Computer Vision, 2005. doi:10.1109/ICCV.2005.166

Markdown

[Pitié et al. "N-Dimensional Probablility Density Function Transfer and Its Application to Colour Transfer." IEEE/CVF International Conference on Computer Vision, 2005.](https://mlanthology.org/iccv/2005/pitie2005iccv-n/) doi:10.1109/ICCV.2005.166

BibTeX

@inproceedings{pitie2005iccv-n,
  title     = {{N-Dimensional Probablility Density Function Transfer and Its Application to Colour Transfer}},
  author    = {Pitié, François and Kokaram, Anil C. and Dahyot, Rozenn},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {2005},
  pages     = {1434-1439},
  doi       = {10.1109/ICCV.2005.166},
  url       = {https://mlanthology.org/iccv/2005/pitie2005iccv-n/}
}