Skip to content

← ArchivePaper2016

BlendForces: A Dynamic Framework for Facial Animation

Vincent Barrielle, Nicolas Stoiber, Cedric Cagniart

CGFAcademic36 cites1 descendantFacial

Treats blendshapes as force bases rather than shape bases, enabling dynamic and physically plausible facial animation and retargeting.

Abstract

In this paper we present a new paradigm for the generation and retargeting of facial animation. Like a vast majority of the approaches that have adressed these topics, our formalism is built on blendshapes. However, where prior works have generally encoded facial geometry using a low dimensional basis of these blendshapes, we propose to encode facial dynamics by looking at blendshapes as a basis of forces rather than a basis of shapes . We develop this idea into a dynamic model that naturally combines the blendshapes paradigm with physics‐based techniques for the simulation of deforming meshes. Because it escapes the linear span of the shape basis through time‐integration and physics‐inspired simulation, this approach has a wider expressive range than previous blendshape‐based methods. Its inherent physically‐based formulation also enables the simulation of more advanced physical interactions, such as collision responses on lip contacts.

How to read this

Category
Method: a physics-based dynamic framework for facial animation
Contributions
  • Reframes blendshapes as a basis of forces rather than a basis of shapes, encoding facial dynamics instead of static geometry
  • Develops a dynamic model combining the blendshape paradigm with physics-based deforming-mesh simulation and time integration
  • Achieves a wider expressive range than linear blendshape methods and enables physical interactions such as lip-contact collision responses
Context
Departs from the standard linear blendshape control of Lewis and Anjyo's direct-manipulation blendshapes (lewis-direct-manipulation-blendshapes-2010) by recasting the basis within a physics simulation.Builds on: Direct Manipulation Blendshapes
Correctness
The central assumption is that treating blendshapes as forces driving a simulated mesh yields more plausible dynamics than linear shape blending; the gains rest on the physics model and integration, and a reader should weigh added simulation cost against the expressiveness benefit.
Clarity
Conceptually elegant but formally dense; a first pass conveys the forces-not-shapes reframing, the simulation math needs a careful second pass.
How to read it
Read first to grasp the forces-as-basis idea and why it escapes the linear span; a second (and likely third) pass is worth it for the dynamic model and time-integration formulation.

Builds on

Built upon by

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 →