bibtype C - Conference Paper (international conference)
ARLID 0433357
utime 20240111140852.6
mtime 20141023235959.9
title (primary) (eng) A Probabilistic Approach to Rough Texture Compression and Rendering
specification
page_count 5 s.
media_type E
serial
ARLID cav_un_epca*0433356
title MUSCLE International Workshop on Computational Intelligence for Multimedia Understanding
page_num 8-12
publisher
place Antalya, Turkey
name Bilkent University
year 2013
keyword rough texture
keyword BTF compression
keyword mixture model
author (primary)
ARLID cav_un_auth*0101086
name1 Filip
name2 Jiří
full_dept (cz) Rozpoznávání obrazu
full_dept (eng) Department of Pattern Recognition
department (cz) RO
department (eng) RO
institution UTIA-B
full_dept Department of Pattern Recognition
fullinstit Ústav teorie informace a automatizace AV ČR, v. v. i.
author
ARLID cav_un_auth*0101091
name1 Grim
name2 Jiří
full_dept (cz) Rozpoznávání obrazu
full_dept Department of Pattern Recognition
department (cz) RO
department RO
institution UTIA-B
full_dept Department of Pattern Recognition
fullinstit Ústav teorie informace a automatizace AV ČR, v. v. i.
author
ARLID cav_un_auth*0101093
name1 Haindl
name2 Michal
full_dept (cz) Rozpoznávání obrazu
full_dept Department of Pattern Recognition
department (cz) RO
department RO
institution UTIA-B
full_dept Department of Pattern Recognition
fullinstit Ústav teorie informace a automatizace AV ČR, v. v. i.
source
source_type hypertextový soubor PDF
url http://library.utia.cas.cz/separaty/2014/RO/filip-0433357.pdf
source_size 1.3MB
cas_special
project
project_id GA14-10911S
agency GA ČR
country CZ
ARLID cav_un_auth*0303439
project
project_id GA14-02652S
agency GA ČR
country CZ
ARLID cav_un_auth*0303412
project
project_id GAP103/11/0335
agency GA ČR
ARLID cav_un_auth*0273627
abstract (eng) Rough textures describe a general visual appearance of real-world materials with regard to view and illumination directions. As the massive size and dimensionality of such representations is a main limitation of their broader use, efficient parameterization and compression methods are needed. Our method is based on estimating the joint probability density of the included nine spatial, directional, and spectral variables in the form of a Gaussian mixture of product components. Our reflectance prediction formula can be expressed analytically as a simple continuous function of input variables and allows fast analytic evaluation for arbitrary spatial and directional values without need for a lengthy interpolation from a finite grid of angular measurements. This method achieves high compression ratio increasing linearly with texture spatial resolution.
action
ARLID cav_un_auth*0308157
name MUSCLE International Workshop on Computational Intelligence for Multimedia Understanding
place Antalya
dates 03.10.2013-04.10.2013
country TR
reportyear 2015
RIV BD
num_of_auth 3
presentation_type PR
inst_support RVO:67985556
permalink http://hdl.handle.net/11104/0237782
confidential S
arlyear 2013
mrcbU56 hypertextový soubor PDF 1.3MB
mrcbU63 cav_un_epca*0433356 MUSCLE International Workshop on Computational Intelligence for Multimedia Understanding 8 12 Antalya, Turkey Bilkent University 2013