Probabilistic Character Motion Synthesis using a Hierarchical Deep Latent Variable Model

Simple item page
dc.contributor.authorGhorbani, Saeeden_US
dc.contributor.authorWloka, Caldenen_US
dc.contributor.authorEtemad, Alien_US
dc.contributor.authorBrubaker, Marcus A.en_US
dc.contributor.authorTroje, Nikolaus F.en_US
dc.contributor.editorBender, Jan and Popa, Tiberiuen_US
dc.date.accessioned2020-10-16T06:25:57Z
dc.date.available2020-10-16T06:25:57Z
dc.date.issued2020
dc.description.abstractWe present a probabilistic framework to generate character animations based on weak control signals, such that the synthesized motions are realistic while retaining the stochastic nature of human movement. The proposed architecture, which is designed as a hierarchical recurrent model, maps each sub-sequence of motions into a stochastic latent code using a variational autoencoder extended over the temporal domain. We also propose an objective function which respects the impact of each joint on the pose and compares the joint angles based on angular distance. We use two novel quantitative protocols and human qualitative assessment to demonstrate the ability of our model to generate convincing and diverse periodic and non-periodic motion sequences without the need for strong control signals.en_US
dc.description.number8
dc.description.sectionheadersCharacter Animation 2
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume39
dc.identifier.doi10.1111/cgf.14116
dc.identifier.issn1467-8659
dc.identifier.pages225-239
dc.identifier.urihttps://doi.org/10.1111/cgf.14116
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf14116
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectComputing methodologies
dc.subjectAnimation
dc.subjectMachine learning approaches
dc.titleProbabilistic Character Motion Synthesis using a Hierarchical Deep Latent Variable Modelen_US
Files
Collections
39-Issue 8