INCO Copernicus project no. 960174
 
 
Texture Synthesis Using Single-Scale / Multiple-Scale Markov Random Field Models
 
Michal Haindl     Vojtech Havlicek




This fast multigrid colour texture synthesis algorithm starts with spectral factorization of an input colour texture image using the Karhunen-Loeve expansion. Single orthogonal monospectral components are further decomposed into a multi-resolution grid and each resolution factors are independently modeled by their dedicated Markov random field model. Finally single synthesized monospectral single-resolution texture factorss are collapsed into the fine resolution images and using the inverse Karhunen-Loeve transformation we obtain the required colour texture.

The multiresolution algorithm.

Examples

Natural textures (upper row) and their synthetic counterparts.


 
The armchairs scene (left) and its virtual model covered with synthetic upholstery, wood, wallpaper and carpet colour textures.



  
    Distributed texture synthesis using a single-scale / multiple-scale MRF models (requires enabled Java applets).
Animated version of the web distributed modification of the algorithm.



Further information can be found in the papers:
RAAD'98
Haindl, M. Havlicek, V.
Multiresolution Colour Texture Synthesis
In: Proceedings 7th Int. Workshop RAAD'98, K. Dobrovodsky Ed., ISBN: 80-967962-7-5, ASCO Art & Science, pp. 297 - 302, 1998.

Textures 2002
Haindl, M. Havlicek, V.
A Simple Multispectral Multiresolution Markov Texture Model
In: Proceedings Texture 2002, The 2nd international workshop on texture analysis and synthesis, Copenhagen 2002, M. Chantler Ed., ISBN 0-901658-99-5, pp. 63-66, Heriot-Watt University.



   Back to the demonstration page.