← ArchivePaper2007
Reusable Facial Rigging and Animation: Create Once, Use Many
PhD thesis on a portable facial pipeline: build a sophisticated rig once on a generic model, then automatically transfer its controls, anatomy and animation to many different face models.
Abstract
A PhD thesis on a portable facial rigging and animation framework. A sophisticated facial rig, including controls, anatomical structure and animation, is built once on a generic model and then transferred automatically to many different 3D face models. The approach cuts the manual cost of facial setup and lets the same deformation parameters drive unique expressions across characters of varying topology and proportion.
How to read this
- Category
- PhD thesis: portable, reusable facial rigging and animation
- Contributions
- A framework where a sophisticated facial rig (controls, anatomy, and animation) is built once on a generic model.
- Automatic transfer of that rig to many different 3D face models of varying topology and proportion.
- Reuse of the same deformation parameters to drive unique expressions per character, cutting manual facial-setup cost.
- Context
- Consolidates and extends the author's create-once, use-many line of work, building on Transferring Facial Expressions to Different Face Models and Sumner and Popovic's Deformation Transfer for Triangle Meshes.Builds on: Transferring Facial Expressions to Different Face Models · Deformation Transfer for Triangle Meshes
- Correctness
- Presented as a thesis-scale pipeline validated by transfer across multiple faces; as with the underlying transfer method, results hinge on correspondence quality and anatomy adaptation across differing topologies, so consistency on highly stylized faces is a reasonable caution.
- Clarity
- As a thesis it is broad and self-contained; a first pass via the introduction and contributions chapters conveys the whole approach, with specific chapters for the formulation.
- How to read it
- Read the intro and contribution summary first for the overall pipeline; dive into the transfer chapters for detail, and treat the 2006 paper as the compact version of the core method.
Builds on
Related work
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 →