← ArchivePaper2006
Transferring a Labeled Generic Rig to Animate Face Models
Adapts a generic facial rig to different face models through a labelling system that carries muscles and skeleton across, so the same deformation parameters give each face its own expressions.
Abstract
We present a facial deformation system that adapts a generic facial rig into different face models. The deformation is based on labels and allows transferring specific facial features between the generic rig and face models. High quality physics-based animation is achieved by combining different deformation methods with our labeling system, which adapts muscles and skeletons from a generic rig to individual face models. We describe how to find the correspondence of the main attributes of the generic rig, transfer them to different 3D face models and generate a sophisticated facial rig based on human anatomy. We show how to apply the same deformation parameters to different face models and obtain unique expressions. Our goal is to ease the character setup process and provide digital artists with a tool that allows manipulating models as if they were using a puppet. We end with different examples that show the strength of our proposal.
How to read this
- Category
- Conference paper on facial rig transfer, the anatomy-based branch of the Porto and UPC line.
- Contributions
- A labelling system that marks the main attributes of a generic facial rig so they can be matched to an arbitrary target face.
- A transfer procedure that carries muscles and skeleton, not just surface shapes, from the generic rig onto each individual model.
- The claim that one set of deformation parameters, replayed on different faces, yields expressions that read as unique per character.
- A framing of the whole thing as a puppet: the artist manipulates the model rather than rebuilding its setup.
- Context
- Sits directly on top of orvalho-facial-transfer-2006, which had already shown expressions moving between face models. This paper is where the generic rig itself becomes the transferable object and gets labelled to make that possible, and it is the formulation the later journal account, orvalho-rig-transfer-2008, expands.Builds on: Transferring Facial Expressions to Different Face Models
- Correctness
- The evidence is a set of worked examples across face models, not a quantitative study, so read the claims as an existence proof of the pipeline rather than a measured result. The anatomical layer is the soft spot: adapting muscles and a skeleton by correspondence assumes the target face is close enough in proportion to the generic one, and the paper does not chart where that assumption fails.
- Clarity
- Short and readable, in the compact AMDO chapter format. The labelling idea is easy to follow, the deformation details are compressed, and you will get more out of the figures than the equations.
- How to read it
- First pass: the abstract and the figures, to see what the labels are attached to. Second pass: the correspondence section, and hold it next to orvalho-facial-transfer-2006 so you can tell what is new here. Third pass only if you want the muscle and skeleton adaptation in detail, and at that point go to orvalho-rig-transfer-2008 instead, which says the same thing at more length.
Builds on
Built upon by
Nothing yet.
Related work
- Easy Rigging of Face by Automatic Registration and Transfer of Skinning Parameters 2010 / ICCVG
- Reusable Facial Rigging and Animation: Create Once, Use Many 2007 / PhD Thesis
- Transferring Facial Expressions to Different Face Models 2006 / SIACG
- Transferring the Rig and Animations from a Character to Different Face Models 2008 / CGF
Keywords
This page summarises the entry and links to its original source. The archive never hosts or redistributes the publication itself.Show it in the full archive list →