Název: Comparing GPLVM approaches for dimensionality reduction in character animation
Autoři: Quirion, Sébastien
Duchesne, Chantale
Laurendeau, Denis
Marchand, Mario
Citace zdrojového dokumentu: Journal of WSCG. 2008, vol. 16, no. 1-3, p. 41-48.
Datum vydání: 2008
Nakladatel: Václav Skala - UNION Agency
Typ dokumentu: article
článek
URI: http://hdl.handle.net/11025/1319
http://wscg.zcu.cz/wscg2008/Papers_2008/journal/!_WSCG2008_Journal_final.zip
ISBN: 978-80-86943-14-5
ISSN: 1213–6972 (hardcopy)
1213–6980 (CD-ROM)
1213–6964 (online)
Klíčová slova: animace postav;Gausovské procesy;model latentních proměnných;redukce dimenzionality;stupně volnosti;nelineární transformace
Klíčová slova v dalším jazyce: character animation;Gaussian process;latent variable models;dimensionality reduction;degrees of freedom;nonlinear transformation
Abstrakt: Gaussian Process Latent Variable Models (GPLVMs) have been found to allow dramatic dimensionality reduction in character animations, often yielding two-dimensional or three-dimensional spaces from which the animation can be retrieved without perceptible alterations. Recently, many researchers have used this approach and improved on it for their purposes, thus creating a number of GPLVM-based approaches. The current paper introduces the main concepts behind GPLVMs and introduces its most widely known variants. Each approach is then compared based on various criteria pertaining to the task of dimensionality reduction in character animation. In the light of our experiments, no single approach is preferred over all others in all respects. Depending whether dimensionality reduction is used for compression purposes, to interpolate new natural looking poses or to synthesize entirely new motions, different approaches will be preferred.
Práva: © Václav Skala - UNION Agency
Vyskytuje se v kolekcích:Number 1-3 (2008)

Soubory připojené k záznamu:
Soubor Popis VelikostFormát 
Quirion.pdf674,16 kBAdobe PDFZobrazit/otevřít


Použijte tento identifikátor k citaci nebo jako odkaz na tento záznam: http://hdl.handle.net/11025/1319

Všechny záznamy v DSpace jsou chráněny autorskými právy, všechna práva vyhrazena.