0462884 20240103212627.520160921235959.9 84988521877 000398736400008 10.1007/978-3-319-43982-2 10 s. P cav_un_epca*0462883978-3-319-43981-52194-535789-98SwitzerlandSpringer Internatiion Publishing2017ZgrzynowaAlexanderChorosKazimierzSieminskiAndrzej bidirectional texture function texture synthesis compound random field model cav_un_auth*0101093 Rozpoznávání obrazu Department of Pattern Recognition RO RO Department of Pattern Recognition Haindl Michal UTIA-B Ústav teorie informace a automatizace AV ČR, v. v. i. cav_un_auth*0283206 Rozpoznávání obrazu Department of Pattern Recognition RO RO Department of Pattern Recognition Havlíček Michal UTIA-B Ústav teorie informace a automatizace AV ČR, v. v. i. http://library.utia.cas.cz/separaty/2016/RO/haindl-0462884.pdf cav_un_auth*0303439 GA14-10911S GA ČR CZ This paper describes a simple novel compound random field model capable of realistic modelling the most advanced recent representation of visual properties of surface materials - the bidirectional texture function. The presented compound random field model combines a non-parametric control random field with local multispectral models for single regions and thus allows to avoid demanding iterative methods for both parameters estimation and the compound random field synthesis. The local textur regions (not necessarily continuous) are represented by an analytical bidirectional texture function model which consists of single scale factors modeled by the three-dimensional moving average random field model which can be analytically estimated as well as synthesized. cav_un_auth*0333803 Multimedia and Network Information Systems MISSI 2016 /10./ 20160914 Wroclaw PL 20160916 BD 10000 10100 10102 2017 2 PR RVO:67985556 http://hdl.handle.net/11104/0262366 S RIV/67985556:_____/17:00462884!RIV17-AV0-67985556 191870806 Doplnení OECD UTIA-B RIV/67985556:_____/17:00462884!RIV17-GA0-67985556 191876837 Doplnění OECD UTIA-B n.a. Proceedings Paper Computer Science Artificial Intelligence|Computer Science Information Systems|Computer Science Theory Methods n.a. Proceedings Paper Computer Science Artificial Intelligence|Computer Science Information Systems|Computer Science Theory Methods n.a. Proceedings Paper Computer Science Artificial Intelligence|Computer Science Information Systems|Computer Science Theory Methods 2017 84988521877 SCOPUS 000398736400008 WOS cav_un_epca*0462883 Multimedia and Network Information Systems 978-3-319-43981-5 2194-5357 89-98 89 98 Switzerland Springer Internatiion Publishing 2017 Advances in Intelligent Systems and Computing 506 Zgrzynowa Alexander 340 Choros Kazimierz 340 Sieminski Andrzej 340