← ArchivePaper2016
Creating an Actor-Specific Facial Rig from Performance Capture
Pipeline for building a personalized facial rig directly from performance-capture data, fitting blendshape bases to actor-specific motion.
Abstract
Creating a high quality blendshape rig usually involves a large amount of effort from skilled artists. Although current 3D reconstruction technologies are able to capture accurate facial geometry of the actor, it is still very difficult to build a production-ready blendshape rig from unorganized scans. Removing rigid head motion and separating mixed expressions from the captures are two of the major challenges in this process. We present a technique that creates a facial blendshape rig based on performance capture and a generic face rig. The customized rig accurately captures actor-specific face details while producing a semantically meaningful FACS basis. The resulting rig faithfully serves both artist friendly keyframe animation and high quality facial motion retargeting in production.
How to read this
- Category
- Method: building an actor-specific facial rig from performance capture
- Contributions
- Creates a customized facial blendshape rig from performance capture plus a generic face rig, capturing actor-specific detail while producing a semantically meaningful FACS basis
- Addresses the two main challenges of removing rigid head motion and separating mixed expressions from unorganized scans
- Produces a rig that serves both artist-friendly keyframe animation and high-quality facial motion retargeting in production
- Context
- Builds on the authors' artist-friendly facial retargeting work (seol-facial-retargeting-2011), turning captured performance into a production-ready, FACS-aligned personalized rig.Builds on: Artist Friendly Facial Animation Retargeting
- Correctness
- Assumes a generic face rig can be specialized to the actor once rigid motion is removed and mixed expressions are separated; presented as a production pipeline (DigiPro), so the reader should view it as a practitioner-validated workflow rather than a broadly benchmarked method.
- Clarity
- Accessible and practitioner-oriented; a first pass conveys the pipeline, a second pass clarifies the motion-separation and basis-fitting steps.
- How to read it
- First pass for the workflow and the two challenges it solves; a second pass is worth it on the rigid-motion removal and expression-separation if you build production facial rigs.
Builds on
Related work
- Facial Retargeting with Automatic Range of Motion Alignment 2017 / SIGGRAPH
- RigAnyFace: Scaling Neural Facial Mesh Auto-Rigging with Unlabeled Data 2025 / arXiv
- Example-Based Facial Rigging 2010 / SIGGRAPH
- Realtime Facial Animation with On-the-fly Correctives 2013 / SIGGRAPH
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 →