View in EDS HTML Full Text PDF Full Text

Deep‐Learning‐Based Facial Retargeting Using Local Patches.

Saved in:
Bibliographic Details
Title: Deep‐Learning‐Based Facial Retargeting Using Local Patches.
Authors: Choi, Yeonsoo1 (AUTHOR) cys219141@alumni.kaist.ac.kr, Lee, Inyup2 (AUTHOR) leeinyup123@kaist.ac.kr, Cha, Sihun2 (AUTHOR) chacorp@kaist.ac.kr, Kim, Seonghyeon3 (AUTHOR) ippx123@gmail.com, Jung, Sunjin2 (AUTHOR) sunjin225@kaist.ac.kr, Noh, Junyong2 (AUTHOR) junyongnoh@kaist.ac.kr
Source: Computer Graphics Forum. Feb2025, Vol. 44 Issue 1, p1-15. 15p.
Subjects: Motion capture (Cinematography), Digital technology, Facial expression, Video processing, Range of motion of joints
Abstract: In the era of digital animation, the quest to produce lifelike facial animations for virtual characters has led to the development of various retargeting methods. While the retargeting facial motion between models of similar shapes has been very successful, challenges arise when the retargeting is performed on stylized or exaggerated 3D characters that deviate significantly from human facial structures. In this scenario, it is important to consider the target character's facial structure and possible range of motion to preserve the semantics assumed by the original facial motions after the retargeting. To achieve this, we propose a local patch‐based retargeting method that transfers facial animations captured in a source performance video to a target stylized 3D character. Our method consists of three modules. The Automatic Patch Extraction Module extracts local patches from the source video frame. These patches are processed through the Reenactment Module to generate correspondingly re‐enacted target local patches. The Weight Estimation Module calculates the animation parameters for the target character at every frame for the creation of a complete facial animation sequence. Extensive experiments demonstrate that our method can successfully transfer the semantic meaning of source facial expressions to stylized characters with considerable variations in facial feature proportion. [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: 183820834
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Deep‐Learning‐Based Facial Retargeting Using Local Patches.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Choi%2C+Yeonsoo%22">Choi, Yeonsoo</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> cys219141@alumni.kaist.ac.kr</i><br /><searchLink fieldCode="AR" term="%22Lee%2C+Inyup%22">Lee, Inyup</searchLink><relatesTo>2</relatesTo> (AUTHOR)<i> leeinyup123@kaist.ac.kr</i><br /><searchLink fieldCode="AR" term="%22Cha%2C+Sihun%22">Cha, Sihun</searchLink><relatesTo>2</relatesTo> (AUTHOR)<i> chacorp@kaist.ac.kr</i><br /><searchLink fieldCode="AR" term="%22Kim%2C+Seonghyeon%22">Kim, Seonghyeon</searchLink><relatesTo>3</relatesTo> (AUTHOR)<i> ippx123@gmail.com</i><br /><searchLink fieldCode="AR" term="%22Jung%2C+Sunjin%22">Jung, Sunjin</searchLink><relatesTo>2</relatesTo> (AUTHOR)<i> sunjin225@kaist.ac.kr</i><br /><searchLink fieldCode="AR" term="%22Noh%2C+Junyong%22">Noh, Junyong</searchLink><relatesTo>2</relatesTo> (AUTHOR)<i> junyongnoh@kaist.ac.kr</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Computer+Graphics+Forum%22">Computer Graphics Forum</searchLink>. Feb2025, Vol. 44 Issue 1, p1-15. 15p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Motion+capture+%28Cinematography%29%22">Motion capture (Cinematography)</searchLink><br /><searchLink fieldCode="DE" term="%22Digital+technology%22">Digital technology</searchLink><br /><searchLink fieldCode="DE" term="%22Facial+expression%22">Facial expression</searchLink><br /><searchLink fieldCode="DE" term="%22Video+processing%22">Video processing</searchLink><br /><searchLink fieldCode="DE" term="%22Range+of+motion+of+joints%22">Range of motion of joints</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: In the era of digital animation, the quest to produce lifelike facial animations for virtual characters has led to the development of various retargeting methods. While the retargeting facial motion between models of similar shapes has been very successful, challenges arise when the retargeting is performed on stylized or exaggerated 3D characters that deviate significantly from human facial structures. In this scenario, it is important to consider the target character's facial structure and possible range of motion to preserve the semantics assumed by the original facial motions after the retargeting. To achieve this, we propose a local patch‐based retargeting method that transfers facial animations captured in a source performance video to a target stylized 3D character. Our method consists of three modules. The Automatic Patch Extraction Module extracts local patches from the source video frame. These patches are processed through the Reenactment Module to generate correspondingly re‐enacted target local patches. The Weight Estimation Module calculates the animation parameters for the target character at every frame for the creation of a complete facial animation sequence. Extensive experiments demonstrate that our method can successfully transfer the semantic meaning of source facial expressions to stylized characters with considerable variations in facial feature proportion. [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=183820834
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1111/cgf.15263
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 15
        StartPage: 1
    Subjects:
      – SubjectFull: Motion capture (Cinematography)
        Type: general
      – SubjectFull: Digital technology
        Type: general
      – SubjectFull: Facial expression
        Type: general
      – SubjectFull: Video processing
        Type: general
      – SubjectFull: Range of motion of joints
        Type: general
    Titles:
      – TitleFull: Deep‐Learning‐Based Facial Retargeting Using Local Patches.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Choi, Yeonsoo
      – PersonEntity:
          Name:
            NameFull: Lee, Inyup
      – PersonEntity:
          Name:
            NameFull: Cha, Sihun
      – PersonEntity:
          Name:
            NameFull: Kim, Seonghyeon
      – PersonEntity:
          Name:
            NameFull: Jung, Sunjin
      – PersonEntity:
          Name:
            NameFull: Noh, Junyong
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 02
              Text: Feb2025
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 01677055
          Numbering:
            – Type: volume
              Value: 44
            – Type: issue
              Value: 1
          Titles:
            – TitleFull: Computer Graphics Forum
              Type: main
ResultId 1