0380283 20240103201154.020120921235959.9 10.1007/978-3-642-32436-9_12 11 s. P cav_un_epca*0380282978-3-642-32435-20302-9743138-148BerlinSpringer2012 compound Markov random field bidirectional texture function texture editing cav_un_auth*0101093 Haindl Michal Rozpoznávání obrazu Department of Pattern Recognition RO RO UTIA-B Department of Pattern Recognition Ústav teorie informace a automatizace AV ČR, v. v. i. cav_un_auth*0101100 Havlíček Vojtěch Rozpoznávání obrazu Department of Pattern Recognition RO RO UTIA-B Department of Pattern Recognition Ústav teorie informace a automatizace AV ČR, v. v. i. http://www.springerlink.com/content/047124j43073m202/ GA102/08/0593 GA ČR cav_un_auth*0239567 1M0572 GA MŠk cav_un_auth*0001814 GAP103/11/0335 GA ČR cav_un_auth*0273627 387/2010 CESNET CZ This paper describes high visual quality compound Markov random field texture model capable to realistically model multispectral bidirectional texture function, which is currently the most advanced representation of visual properties of surface materials. The presented compound Markov random field model combines a non-parametric control random field with analytically solvable wide-sense Markov representation for single regions and thus allows very efficient non-iterative parameters estimation as well as the compound random field synthesis. The compound Markov random field model is utilized for realistic texture compression, enlargement, and powerful automatic texture editing. Edited textures maintain their original layout but adopt anticipated local characteristics from one or several parent target textures. cav_un_auth*0283201 MUSCLE Pisa 13.12.2011-15.12.2011 IT 2013 BD 2 PR http://hdl.handle.net/11104/0211026 100 0.314 16.66 0.49 Q2 Q2 2012 cav_un_epca*0380282 Computational Intelligence for Multimedia Understanding 978-3-642-32435-2 0302-9743 138 148 Berlin Springer 2012 Lecture Notes in Computer Science 7252