Understanding and controlling contrast oscillations in stochastic texture algorithms using Spectrum of Variance

Fabrice Neyret 1 Eric Heitz 2
1 MAVERICK - Models and Algorithms for Visualization and Rendering
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : We identify and analyze a major issue pertaining to all power-spectrum based texture synthesis algorithms – from Fourier synthesis to procedural noise algorithms like Perlin or Gabor noise – , namely, the oscillation of contrast (see Figures 1,2,3,7). One of our key contributions is to introduce a simple yet powerful descriptor of signals, the Spectrum of Variance (not to be confused with the PSD), which, to our surprise, has never been leveraged before. In this new framework, several issues get easy to understand measure and control, with new handles, as we illustrate. We finally show that fixing oscillation of contrast opens many doors to a more controllable authoring of stochastic texturing. We explore some of the new reachable possibilities such as constrained noise content and bridges towards very different families of look such as cellular patterns, points-like distributions or reaction-diffusion.
Document type :
Reports
Complete list of metadatas

https://hal.inria.fr/hal-01349134
Contributor : Fabrice Neyret <>
Submitted on : Tuesday, July 26, 2016 - 7:41:14 PM
Last modification on : Wednesday, June 27, 2018 - 3:46:13 PM
Long-term archiving on : Thursday, October 27, 2016 - 2:26:13 PM

Files

main.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01349134, version 1

Collections

Citation

Fabrice Neyret, Eric Heitz. Understanding and controlling contrast oscillations in stochastic texture algorithms using Spectrum of Variance. [Research Report] LJK / Grenoble University - INRIA. 2016, pp.8. ⟨hal-01349134⟩

Share

Metrics

Record views

695

Files downloads

707