Gaussian-Product Subdivision Surfaces

Reinhold Preiner, Tamy Boubekeur, Michael Wimmer

Research output: Contribution to conferencePaper

Abstract

Probabilistic distribution models like Gaussian mixtures have shown great potential for improving both the quality and speed of several geometric operators. This is largely due to their ability to model large fuzzy data using only a reduced set of atomic distributions, allowing for large compression rates at minimal information loss. We introduce a new surface model that utilizes these qualities of Gaussian mixtures for the definition and control of a parametric smooth surface. Our approach is based on an enriched mesh data structure, which describes the probability distribution of spatial surface locations around each vertex via a Gaussian covariance matrix. By incorporating this additional covariance information, we show how to define a smooth surface via a non-linear probabilistic subdivision operator based on products of Gaussians, which is able to capture rich details at fixed control mesh resolution. This entails new applications in surface reconstruction, modeling, and geometric compression.
Original languageEnglish
Number of pages11
Publication statusPublished - Jul 2019
EventSIGGRAPH 2019 - Los Angeles, United States
Duration: 28 Jul 20191 Aug 2019

Conference

ConferenceSIGGRAPH 2019
CountryUnited States
Period28/07/191/08/19

Keywords

  • Gaussian Mixture
  • GMM
  • Subdivision Surface
  • Gaussian Product
  • Covariance Mesh
  • Nonlinear Subdivision

Fingerprint Dive into the research topics of 'Gaussian-Product Subdivision Surfaces'. Together they form a unique fingerprint.

  • Cite this

    Preiner, R., Boubekeur, T., & Wimmer, M. (2019). Gaussian-Product Subdivision Surfaces. Paper presented at SIGGRAPH 2019, United States.