View in EDS HTML Full Text PDF Full Text

Robust Diffusion‐based Motion In‐betweening.

Saved in:
Bibliographic Details
Title: Robust Diffusion‐based Motion In‐betweening.
Authors: Qin, Jia1 (AUTHOR), Yan, Peng1 (AUTHOR), An, Bo2 (AUTHOR) amberonno@gmail.com
Source: Computer Graphics Forum. Oct2024, Vol. 43 Issue 7, p1-11. 11p.
Subjects: Motion capture (Human mechanics), Animators, Generalization, Encoding, Density
Abstract: The emergence of learning‐based motion in‐betweening techniques offers animators a more efficient way to animate characters. However, existing non‐generative methods either struggle to support long transition generation or produce results that lack diversity. Meanwhile, diffusion models have shown promising results in synthesizing diverse and high‐quality motions driven by text and keyframes. However, in these methods, keyframes often serve as a guide rather than a strict constraint and can sometimes be ignored when keyframes are sparse. To address these issues, we propose a lightweight yet effective diffusion‐based motion in‐betweening framework that generates animations conforming to keyframe constraints. We incorporate keyframe constraints into the training phase to enhance robustness in handling various constraint densities. Moreover, we employ relative positional encoding to improve the model's generalization on long range in‐betweening tasks. This approach enables the model to learn from short animations while generating realistic in‐betweening motions spanning thousands of frames. We conduct extensive experiments to validate our framework using the newly proposed metrics K‐FID, K‐Diversity, and K‐Error, designed to evaluate generative in‐betweening methods. Results demonstrate that our method outperforms existing diffusion‐based methods across various lengths and keyframe densities. We also show that our method can be applied to text‐driven motion synthesis, offering fine‐grained control over the generated results. [ABSTRACT FROM AUTHOR]
Copyright of Computer Graphics Forum is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: egs
DbLabel: Engineering Source
An: 180900518
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Robust Diffusion‐based Motion In‐betweening.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Qin%2C+Jia%22">Qin, Jia</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Yan%2C+Peng%22">Yan, Peng</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22An%2C+Bo%22">An, Bo</searchLink><relatesTo>2</relatesTo> (AUTHOR)<i> amberonno@gmail.com</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Computer+Graphics+Forum%22">Computer Graphics Forum</searchLink>. Oct2024, Vol. 43 Issue 7, p1-11. 11p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Motion+capture+%28Human+mechanics%29%22">Motion capture (Human mechanics)</searchLink><br /><searchLink fieldCode="DE" term="%22Animators%22">Animators</searchLink><br /><searchLink fieldCode="DE" term="%22Generalization%22">Generalization</searchLink><br /><searchLink fieldCode="DE" term="%22Encoding%22">Encoding</searchLink><br /><searchLink fieldCode="DE" term="%22Density%22">Density</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: The emergence of learning‐based motion in‐betweening techniques offers animators a more efficient way to animate characters. However, existing non‐generative methods either struggle to support long transition generation or produce results that lack diversity. Meanwhile, diffusion models have shown promising results in synthesizing diverse and high‐quality motions driven by text and keyframes. However, in these methods, keyframes often serve as a guide rather than a strict constraint and can sometimes be ignored when keyframes are sparse. To address these issues, we propose a lightweight yet effective diffusion‐based motion in‐betweening framework that generates animations conforming to keyframe constraints. We incorporate keyframe constraints into the training phase to enhance robustness in handling various constraint densities. Moreover, we employ relative positional encoding to improve the model's generalization on long range in‐betweening tasks. This approach enables the model to learn from short animations while generating realistic in‐betweening motions spanning thousands of frames. We conduct extensive experiments to validate our framework using the newly proposed metrics K‐FID, K‐Diversity, and K‐Error, designed to evaluate generative in‐betweening methods. Results demonstrate that our method outperforms existing diffusion‐based methods across various lengths and keyframe densities. We also show that our method can be applied to text‐driven motion synthesis, offering fine‐grained control over the generated results. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Computer Graphics Forum is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=180900518
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1111/cgf.15260
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 11
        StartPage: 1
    Subjects:
      – SubjectFull: Motion capture (Human mechanics)
        Type: general
      – SubjectFull: Animators
        Type: general
      – SubjectFull: Generalization
        Type: general
      – SubjectFull: Encoding
        Type: general
      – SubjectFull: Density
        Type: general
    Titles:
      – TitleFull: Robust Diffusion‐based Motion In‐betweening.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Qin, Jia
      – PersonEntity:
          Name:
            NameFull: Yan, Peng
      – PersonEntity:
          Name:
            NameFull: An, Bo
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 10
              Text: Oct2024
              Type: published
              Y: 2024
          Identifiers:
            – Type: issn-print
              Value: 01677055
          Numbering:
            – Type: volume
              Value: 43
            – Type: issue
              Value: 7
          Titles:
            – TitleFull: Computer Graphics Forum
              Type: main
ResultId 1