Motion In-Betweening with Phase Manifolds

Simple item page
dc.contributor.authorStarke, Paulen_US
dc.contributor.authorStarke, Sebastianen_US
dc.contributor.authorKomura, Takuen_US
dc.contributor.authorSteinicke, Franken_US
dc.contributor.editorWang, Huaminen_US
dc.contributor.editorYe, Yutingen_US
dc.contributor.editorVictor Zordanen_US
dc.date.accessioned2023-10-16T12:33:06Z
dc.date.available2023-10-16T12:33:06Z
dc.date.issued2023
dc.description.abstractThis paper introduces a novel data-driven motion in-betweening system to reach target poses of characters by making use of phases variables learned by a Periodic Autoencoder. Our approach utilizes a mixture-of-experts neural network model, in which the phases cluster movements in both space and time with different expert weights. Each generated set of weights then produces a sequence of poses in an autoregressive manner between the current and target state of the character. In addition, to satisfy poses which are manually modified by the animators or where certain end effectors serve as constraints to be reached by the animation, a learned bi-directional control scheme is implemented to satisfy such constraints. The results demonstrate that using phases for motion in-betweening tasks sharpen the interpolated movements, and furthermore stabilizes the learning process. Moreover, using phases for motion in-betweening tasks can also synthesize more challenging movements beyond locomotion behaviors. Additionally, style control is enabled between given target keyframes. Our proposed framework can compete with popular state-of-the-art methods for motion in-betweening in terms of motion quality and generalization, especially in the existence of long transition durations. Our framework contributes to faster prototyping workflows for creating animated character sequences, which is of enormous interest for the game and film industry.en_US
dc.description.number3
dc.description.sectionheadersCharacter Synthesis
dc.description.seriesinformationProceedings of the ACM on Computer Graphics and Interactive Techniques
dc.description.volume6
dc.identifier.doi10.1145/3606921
dc.identifier.issn2577-6193
dc.identifier.urihttps://doi.org/10.1145/3606921
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1145/3606921
dc.publisherACM Association for Computing Machineryen_US
dc.subjectCCS Concepts: Computing methodologies -> Motion capture; Neural networks Additional KeyWords and Phrases: animation system, transition generation, locomotion, character animation, animation with constraints, data driven animation, deep learning"
dc.subjectComputing methodologies
dc.subjectMotion capture
dc.subjectNeural networks Additional KeyWords and Phrases
dc.subjectanimation system
dc.subjecttransition generation
dc.subjectlocomotion
dc.subjectcharacter animation
dc.subjectanimation with constraints
dc.subjectdata driven animation
dc.subjectdeep learning"
dc.titleMotion In-Betweening with Phase Manifoldsen_US
Files
Collections
SCA 2023: Eurographics/SIGGRAPH Symposium on Computer Animation