Bitte benutzen Sie diese Referenz, um auf diese Ressource zu verweisen: doi:10.22028/D291-40489
Volltext verfügbar? / Dokumentlieferung
Titel: Learning a Continuous Control of Motion Style from Natural Examples
VerfasserIn: Sprenger, Janis
Du, Han
Cheema, Noshaba
Herrmann, Erik
Fischer, Klaus
Slusallek, Philipp
HerausgeberIn: Shum, Hubert P. H.
Ho, Edmond S. L.
Cani, Marie-Paule
Popa, Tiberiu
Holden, Daniel
Wang, He
Sprache: Englisch
Titel: Motion, Interaction and Games
Verlag/Plattform: ACM
Erscheinungsjahr: 2019
Erscheinungsort: New York
Konferenzort: Newcastle upon Tyne, United Kingdom
DDC-Sachgruppe: 004 Informatik
Dokumenttyp: Konferenzbeitrag (in einem Konferenzband / InProceedings erschienener Beitrag)
Abstract: The simulation of humanoid avatars is relevant for a multitude of applications, such as movies, games, simulations for autonomous vehicles, virtual avatars and many more. In order to achieve the simulation of realistic and believable characters, it is important to simulate motion with the natural motion style matching the character’s characteristic. A female avatar, for example, should move in a female style and different characters should vary in their expressiveness of this style. However, the manual definition, as well as the acting of a natural female or male style, is non-trivial. Previous work on style transfer is insufficient, as the style examples are not necessarily a natural depiction of female or male locomotion. We propose a novel data-driven method to infer the style information based on individual samples of male and female motion capture data. For this purpose, the data of 12 female and 12 male participants was captured in an experimental setting. A neural network based motion model is trained for each participant and the style dimension is learned in the latent representation of these models. Thus a linear style model is inferred on top of the motion models. It can be utilized to synthesize network models of different style expressiveness on a continuous scale while retaining the performance and content of the original network model. A user study supports the validity of our approach while highlighting issues with simpler approaches to infer the style.
DOI der Erstveröffentlichung: 10.1145/3359566.3360082
URL der Erstveröffentlichung: https://dl.acm.org/doi/10.1145/3359566.3360082
Link zu diesem Datensatz: urn:nbn:de:bsz:291--ds-404890
hdl:20.500.11880/36392
http://dx.doi.org/10.22028/D291-40489
ISBN: 978-1-4503-6994-7
Datum des Eintrags: 5-Sep-2023
Fakultät: MI - Fakultät für Mathematik und Informatik
Fachrichtung: MI - Informatik
Professur: MI - Prof. Dr. Philipp Slusallek
Sammlung:SciDok - Der Wissenschaftsserver der Universität des Saarlandes

Dateien zu diesem Datensatz:
Es gibt keine Dateien zu dieser Ressource.


Alle Ressourcen in diesem Repository sind urheberrechtlich geschützt.