Making Gabor Noise Fast and Normalized

Vincent Tavernier 1 Fabrice Neyret 1 Romain Vergne 1 Joëlle Thollot 1
1 MAVERICK - Models and Algorithms for Visualization and Rendering
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : Gabor Noise is a powerful procedural texture synthesis technique, but has two major drawbacks: It is costly due to the high required splat density and not always predictable because properties of instances can differ from those of the process. We bench performance and quality using alternatives for each Gabor Noise ingredient: point distribution, kernel weighting and kernel shape. For this, we introduce 3 objective criteria to measure process convergence, process stationarity, and instance stationarity. We show that minor implementation changes allow for 17 − 24× speed-up with same or better quality.
Document type :
Conference papers
Complete list of metadatas
Contributor : Vincent Tavernier <>
Submitted on : Friday, April 19, 2019 - 2:49:53 PM
Last modification on : Thursday, April 25, 2019 - 4:52:19 PM


  • HAL Id : hal-02104389, version 1



Vincent Tavernier, Fabrice Neyret, Romain Vergne, Joëlle Thollot. Making Gabor Noise Fast and Normalized. Eurographics, May 2019, Gênes, Italy. pp.1-4. ⟨hal-02104389⟩



Record views


Files downloads