Local random-phase noise for procedural texturing

Local random-phase noise is an efficient noise model for procedural texturing. It is defined on a regular spatial grid by local noises, which are sums of cosines with random phase. Our model is versatile thanks to separate samplings in the spatial and spectral domains. Therefore, it encompasses Gabor noise and noise by Fourier series. A stratified spectral sampling allows for a faithful yet compact and efficient reproduction of an arbitrary power spectrum. Noise by example is therefore obtained faster than state-of-the-art techniques. As a second contribution we address texture by example and generate not only Gaussian patterns but also structured features present in the input. This is achieved by fixing the phase on some part of the spectrum. Generated textures are continuous and non-repetitive. Results show unprecedented framerates and a flexible visual result: users can modify noise parameters to interactively edit visual variants.

D. Ghazanfarpour

ACM Transactions on Graphics , Volume 33 , Number 6 , page 195:1-195-11 - 2014

International journal Local random-phase noise for procedural texturing, ACM Transactions on Graphics, Association for Computing Machinery (ACM) ( IF : 5.414, SNIP : 3.249, SJR : 2.153 ), pages 195:1-195-11, Volume 33, n° 6, novembre 2014, doi:10.1145/2661229.2661249 Research team : IGG

@Article{2-GSVD14,
author = {Gilet, G. and Sauvage, B. and Vanhoey, K. and Dischler, J-M. and Ghazanfarpour, D.},
title = {Local random-phase noise for procedural texturing},
journal = {ACM Transactions on Graphics},
number = {6},
volume = {33},
pages = {195:1-195-11},
month = {Nov},
year = {2014},
doi = {10.1145/2661229.2661249},
x-international-audience = {Yes},
x-language = {EN},
url = {http://icube-publis.unistra.fr/2-GSVD14}
}


See publications of the same authors