Publications

Detailed Information

Conditional motion in-betweening

DC Field Value Language
dc.contributor.authorKim, Jihoon-
dc.contributor.authorByun, Taehyun-
dc.contributor.authorShin, Seungyoun-
dc.contributor.authorWon, Jungdam-
dc.contributor.authorChoi, Sungjoon-
dc.date.accessioned2024-05-08T05:35:11Z-
dc.date.available2024-05-08T05:35:11Z-
dc.date.created2024-05-08-
dc.date.issued2022-12-
dc.identifier.citationPattern Recognition, Vol.132, p. 108894-
dc.identifier.issn0031-3203-
dc.identifier.urihttps://hdl.handle.net/10371/201170-
dc.description.abstractMotion in-betweening (MIB) is a process of generating intermediate skeletal movement between the given start and target poses while preserving the naturalness of the motion, such as periodic footstep motion while walking. Although state-of-the-art MIB methods are capable of producing plausible mo-tions given sparse key-poses, they often lack the controllability to generate motions satisfying the se-mantic contexts required in practical applications. We focus on the method that can handle pose or se-mantic conditioned MIB tasks using a unified model. We also present a motion augmentation method to improve the quality of pose-conditioned motion generation via defining a distribution over smooth tra-jectories. Our proposed method outperforms the existing state-of-the-art MIB method in pose prediction errors while providing additional controllability. Our code and results are available on our project web page: https://jihoonerd.github.io/Conditional- Motion- In- Betweening . (c) 2022 The Authors. Published by Elsevier Ltd. This is an open access article under the CC BY license ( http://creativecommons.org/licenses/by/4.0/ )-
dc.language영어-
dc.publisherPergamon Press-
dc.titleConditional motion in-betweening-
dc.typeArticle-
dc.identifier.doi10.1016/j.patcog.2022.108894-
dc.citation.journaltitlePattern Recognition-
dc.identifier.wosid000860987400001-
dc.identifier.scopusid2-s2.0-85135127836-
dc.citation.startpage108894-
dc.citation.volume132-
dc.description.isOpenAccessY-
dc.contributor.affiliatedAuthorWon, Jungdam-
dc.type.docTypeArticle-
dc.description.journalClass1-
dc.subject.keywordAuthorMotion in-betweening-
dc.subject.keywordAuthorConditional motion generation-
dc.subject.keywordAuthorGenerative model-
dc.subject.keywordAuthorMotion data augmentation-
Appears in Collections:
Files in This Item:
There are no files associated with this item.

Related Researcher

  • College of Engineering
  • Dept. of Computer Science and Engineering
Research Area Computational Performance, Computer Graphics, Machine Learning, Robotics

Altmetrics

Item View & Download Count

  • mendeley

Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.

Share