0397609 20240103203125.220131112235959.9 8 s. E cav_un_epca*0397608978-80-223-3377-11335-569413-20BratislavaACM, Comenius University2013 dynamic texture texture enlargement tile-based texture synthesis 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*0295135 Richtr Radek 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://library.utia.cas.cz/separaty/2013/RO/haindl-0397609.pdf GA102/08/0593 GA ČR cav_un_auth*0239567 GAP103/11/0335 GA ČR cav_un_auth*0273627 A simple fast approach for dynamic texture synthesize that realistically matches given color or multispectral texture appearance and respects its original optic flow is presented. The method generalizes the prominent static double toroid-shaped texture modeling method to the dynamic texture synthesis domain. The analytical part of the method is based on optimal overlapping tiling and subsequent minimum boundary cut. The optimal toroid-shaped dynamic texture patches are created in each spatial and time dimension, respectively. The time dimension tile border is derived from the optical flow of the modeled texture. The toroid-shaped tiles are created in the analytical step which is completely separated from the synthesis part. Thus the presented method is extremely fast and capable to enlarge a learned natural dynamic texture spatially and temporally in real-time. cav_un_auth*0295136 29th Spring conference on Computer Graphics (SCCG) Smolenice castle 01.05.2013-03.05.2013 SK 2014 BD 2 PR RVO:67985556 http://hdl.handle.net/11104/0225915 2013 cav_un_epca*0397608 Proceedings of the 29th Spring conference on Computer Graphics (SCCG) 978-80-223-3377-1 1335-5694 13 20 Bratislava ACM, Comenius University 2013