CoChat
Sign Up
Cited by 5Human Motion and Animation3D Shape Modeling and AnalysisComputer Graphics and Visualization Techniques

Fast and reusable facial rigging and animation

Open access
Orvalho, Verónica Costa, Susin, Antonio·2007·ACM SIGGRAPH 2007 sketches
DOI 10.1145/1278780.1278856
Open this paper in CoChat — free accountOpen PDF

Abstract

Reproducing the subtleties of a face through animation requires developing a sophisticated character rig. But, creating by hand the inner structure and controls of each character is a very labor-intensive and time-consuming task. We developed an application that is 90--99% faster than traditional manual rigging. The application automatically transfers the rig and animations from the source to a target model. Unlike prior work related to morphing and re-targeting [1] that focus on transferring animations, we transfer the complete facial setup in addition to animations. Our method is general, so artists can define their own rig and then quickly apply it to different models, even with disparate proportions and appearance (human, cartoon or fantastic). This gives artists complete freedom to manipulate the characters: they can create new animations and not be limited by pre-generated ones.

Integrity signals

Registry

Crossref · 10.1145/1278780.1278856

Cites

2 of 2 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Claims the paper makes

0 of 1 cited sources checked · 0 supported · 0 flagged

  • Findingnone given

    The skinning binds the transferred attributes to the target model using the adjusted weights of the source, avoiding the need for manual weighting.

    “It binds the transferred attributes to the target model using the adjusted weights of the source, avoiding the need for manual weighting.”
    Quote in the paperSubstantial claim
  • Findingreasoning

    The method accurately places the source rig attributes into the target model, even if they have different geometric proportions.

    “Next, using as reference the previously deformed source surface, we name guide model, the method accurately places the source rig attributes into the target model, even if they have different geometric proportions.”
    Quote in the paperSubstantial claim
  • Findingreasoning

    The developed application is 90-99% faster than traditional manual rigging.

    “We developed an application that is 90-99% faster than traditional manual rigging.”
    Quote in the paperSubstantial claim
  • Findingown data

    Artists can complete in one hour tasks that before took them one or two weeks of work.

    “The tests showed that artists can complete in one hour, tasks that before took them one or two weeks of work”
    Quote in the paperSubstantial claim
  • Findingnone given

    An application in Maya was created that can handle simple and complex rigs based on a new approach.

    “We created an application in Maya that can handle simple and complex rigs based on a new approach.”
    Quote in the paperSubstantial claim
    • Rests on an assumption: Creating and placing by hand each component of the rig quickly becomes impractical when complexity grows.
  • May combine two claims. 5
  • Classified as probably not a substantial claim. 7

  • May combine two claims.

    Findingnone given

    If the source rig quality is low, the transference is still successful but results on the target will be of comparable quality.

    “If the source rig quality is low, the transference is still successful but results on the target will be of comparable quality.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).

    Findingnone given

    The source and target models can have different descriptors: one can be a polygonal mesh and the other a NURBS surface.

    “The source and target models can have different descriptors: one can be defined as a polygonal mesh and the other as a NURBS surface.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Findingnone given

    The method allows re-adjusting the source rig and rapidly propagating the modifications to all the characters.

    “We allow re-adjusting the source rig and rapidly propagate the modifications to all the characters.”
    Quote in the paperSubstantial claim
    • Rests on an assumption: Minor artistic modifications to geometry or topology force restarting most of the rigging process from scratch, making it impossible to re-use the same rig across different face models.

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Findingnone given

    Several videogame and film companies (Electronic Arts, Radical Entertainment (Canada) and Dygrafilms (Spain)) integrated the application into their pipelines and used it for testing.

    “Several videogame and film companies integrated our application into their pipelines and used it for testing: Electronic Arts, Radical Entertainment (Canada) and Dygrafilms (Spain).”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Findingown data

    Changing weights, modifying an animation control position, or transferring animations between characters can be achieved instantly.

    “something like changing the weights, modifying an animation control position or transferring animations between characters can be achieved”
    Quote in the paperSubstantial claim

  • Classified as probably not a substantial claim.

    Findingnone given

    Another key feature is the flexibility it allows when defining the facial rig.

    “Another key feature is the flexibility it allows when defining the facial rig.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S4 (based).

    Findingnone given

    The faces do not need to have a point-to-point correspondence.

    “Also, the faces do not need to have a point-to-point correspondence.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S4 (based).

    Interpretationreasoning

    It is now possible to animate characters that before were devoid of expression, because of the time it takes to manually create a rig.

    “It is now possible to animate characters that before were devoid of expression, because of the time it takes to manually create a rig.”
    Quote in the paperNot a substantial claim

  • Classified as probably not a substantial claim.

    Study design and conductnone given

    The tests compared the target rigs automatically created by the application to the ones manually created by the artists.

    “Our tests compared the target rigs automatically created by the application to the ones manually created by the artists.”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Interpretationnone given

    The method is general, allowing artists to define their own rig and quickly apply it to different models, even with disparate proportions and appearance (human, cartoon or fantastic).

    “Our method is general, so artists can define their own rig and then quickly apply it to different models, even with disparate proportions and appearance (human, cartoon or fantastic).”
    Quote in the paperNot a substantial claim
    • Rests on an assumption: Minor artistic modifications to geometry or topology force restarting most of the rigging process from scratch, making it impossible to re-use the same rig across different face models.

  • Classified as probably not a substantial claim. May combine two claims.

    Interpretationnone given

    The modular structure makes it simple to integrate into existing animation pipelines and speed up the overall production.

    “The modular structure makes it simple to integrate into existing animation pipelines and speed up the overall production.”
    Quote in the paperSubstantial claim
11 of 11

  • The paper relies on this without support.

    Minor artistic modifications to geometry or topology force restarting most of the rigging process from scratch, making it impossible to re-use the same rig across different face models.

    “Today, any minor artistic modification that causes the model to change in geometry (a smaller nose, a larger eyebrow) or topology (more resolution around the eyes) leads to the re-starting of most of the rigging process from scratch, making it impossible to re-use the same rig in different face models.”

  • The paper relies on this without support.

    Creating and placing by hand each component of the rig quickly becomes impractical when complexity grows.

    “Creating and placing by hand each component of the rig (bones, muscles,...) quickly becomes impractical when complexity grows.”
2 of 2

Cites

Flagged first, then by citations

Cited by

Sorted by citations

Related

Authors
Orvalho, V. C., & Susin, A.
Affiliations
  • Universitat Politècnica de Catalunya (ES)
  • Universitat Politècnica de Catalunya
ORCID
Orvalho, Verónica Costa
Venue
ACM SIGGRAPH 2007 sketches
Publisher
ACM
Published
2007-08-05
Pages
63
DOI
10.1145/1278780.1278856
OpenAlex
W2056008918
Cited by
5
References
2
Citations by year
2020: 1 · 2016: 1
FWCI
1.14
Type
conference paper
Language
en
Open access
Licence
Locations
  • ACM SIGGRAPH Conference (SIGGRAPH) (publishedVersion)
  • UPCommons institutional repository (Universitat Politècnica de Catalunya) (submittedVersion, other-oa)
  • RECERCAT (Consorci de Serveis Universitaris de Catalunya) (submittedVersion, public-domain)
Topics
  • Physical Sciences › Engineering › Control and Systems Engineering › Human Motion and Animation
  • Physical Sciences › Engineering › Computational Mechanics › 3D Shape Modeling and Analysis
  • Physical Sciences › Computer Science › Computer Graphics and Computer-Aided Design › Computer Graphics and Visualization Techniques
Keywords
facial rigging, facial animation, character animation, face morphing

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Claims read by deepseek-v4.1-flash under definition version 3 (extract-v3) on 2026-10-11.

Classified by jev-1.13-20260917 (gold-guideline-v0.2) on 2026-10-11.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review