Stylistic Locomotion Modeling with Conditional Variational Autoencoder

dc.contributor.authorDu, Hanen_US
dc.contributor.authorHerrmann, Eriken_US
dc.contributor.authorSprenger, Janisen_US
dc.contributor.authorCheema, Noshabaen_US
dc.contributor.authorhosseini, somayehen_US
dc.contributor.authorFischer, Klausen_US
dc.contributor.authorSlusallek, Philippen_US
dc.contributor.editorCignoni, Paolo and Miguel, Ederen_US
dc.date.accessioned2019-05-05T17:49:41Z
dc.date.available2019-05-05T17:49:41Z
dc.date.issued2019
dc.description.abstractWe propose a novel approach to create generative models for distinctive stylistic locomotion synthesis. The approach is inspired by the observation that human styles can be easily distinguished from a few examples. However, learning a generative model for natural human motions which display huge amounts of variations and randomness would require a lot of training data. Furthermore, it would require considerable efforts to create such a large motion database for each style. We propose a generative model to combine the large variation in a neutral motion database and style information from a limited number of examples. We formulate the stylistic motion modeling task as a conditional distribution learning problem. Style transfer is implicitly applied during the model learning process. A conditional variational autoencoder (CVAE) is applied to learn the distribution and stylistic examples are used as constraints. We demonstrate that our approach can generate any number of natural-looking human motions with a similar style to the target given a few style examples and a neutral motion database.en_US
dc.description.sectionheadersAnimation and Simulation
dc.description.seriesinformationEurographics 2019 - Short Papers
dc.identifier.doi10.2312/egs.20191002
dc.identifier.issn1017-4656
dc.identifier.pages9-12
dc.identifier.urihttps://doi.org/10.2312/egs.20191002
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/egs20191002
dc.publisherThe Eurographics Associationen_US
dc.subjectComputing methodologies
dc.subjectAnimation
dc.subjectMotion processing
dc.titleStylistic Locomotion Modeling with Conditional Variational Autoencoderen_US
Files