Skip to Main content Skip to Navigation
Conference papers

Pair Correlation Functions with Free-Form Boundaries for Distribution Inpainting and Decomposition

Abstract : Pair Correlation Functions (PCF) have been recently spreading as a reliable representation for distributions, enabling the efficient synthesis of point-sets, vector textures and object placement from examples. In this work we introduce a triangulation-based local filtering method to extend PCF-based analysis to exemplars with free-form boundaries. This makes PCF applicable to new problems such as the inpainting of missing parts in an input distribution, or the decomposition of complex, non-homogeneous distributions into a set of coherent classes, in which each category of points can be studied together with their intra and inter-class correlations.
Document type :
Conference papers
Complete list of metadata

Cited literature [11 references]  Display  Hide  Download

https://hal.inria.fr/hal-02500803
Contributor : Baptiste Nicolet <>
Submitted on : Friday, March 6, 2020 - 1:16:27 PM
Last modification on : Monday, June 22, 2020 - 10:40:55 AM
Long-term archiving on: : Sunday, June 7, 2020 - 2:44:44 PM

File

short1039_CRC.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02500803, version 1

Collections

Citation

Baptiste Nicolet, Pierre Ecormier-Nocca, Pooran Memari, Marie-Paule Cani. Pair Correlation Functions with Free-Form Boundaries for Distribution Inpainting and Decomposition. Eurographics 2020 short paper proceedings, May 2020, Norrköping, Sweden. ⟨hal-02500803⟩

Share

Metrics

Record views

220

Files downloads

284