← ArchivePaper2012

Spacetime Expression Cloning for Blendshapes

Yeongho Seol, J P Lewis, Jaewoo Seo, Byungkuk Choi, Ken Anjyo, Junyong Noh

Spacetime optimization framework for cloning facial expressions across blendshape rigs while preserving timing and dynamic feel.

Open the paper ↗Trace in the lineage graph

Abstract

The goal of a practical facial animation retargeting system is to reproduce the character of a source animation on a target face while providing room for additional creative control by the animator. This article presents a novel spacetime facial animation retargeting method for blendshape face models. Our approach starts from the basic principle that the source and target movements should be similar. By interpreting movement as the derivative of position with time, and adding suitable boundary conditions, we formulate the retargeting problem as a Poisson equation. Specified (e.g., neutral) expressions at the beginning and end of the animation as well as any user-specified constraints in the middle of the animation serve as boundary conditions. In addition, a model-specific prior is constructed to represent the plausible expression space of the target face during retargeting. A Bayesian formulation is then employed to produce target animation that is consistent with the source movements while satisfying the prior constraints. Since the preservation of temporal derivatives is the primary goal of the optimization, the retargeted motion preserves the rhythm and character of the source movement and is free of temporal jitter.

How to read this

Category: Method: facial retargeting (spacetime optimization)
Contributions: Spacetime retargeting of facial animation onto blendshape rigs by matching movement (the time-derivative of position) rather than absolute pose
Casts the problem as a Poisson equation with neutral end-poses and user constraints as boundary conditions
Adds a model-specific plausible-expression prior in a Bayesian formulation, preserving the source's rhythm and character while leaving room for animator control
Context: Extends artist-friendly facial retargeting (Seol et al. 2011) by reformulating it as a temporal-derivative-preserving spacetime optimization.Builds on: Artist Friendly Facial Animation Retargeting
Correctness: Built on the principle that source and target movements should be similar; preserving temporal derivatives keeps timing and dynamic feel, but output realism depends on the target prior and on how well the source rig maps to the target blendshape basis.
Clarity: Conceptually clear (match motion, not pose); a first pass gives the idea, a second pass is needed for the Poisson and Bayesian formulation.
How to read it: First grasp the movement-preservation principle and the boundary-condition setup; a second pass on the Poisson equation and the prior pays off if facial retargeting fidelity is your concern.

Builds on

Artist Friendly Facial Animation Retargeting 2011

Built upon by

Nothing yet.

Related work

Artist Friendly Facial Animation Retargeting 2011 / SIGGRAPH Asia
A Facial Composite Editor for Blendshape Characters 2012 / DigiPro
Adult2Child: Motion Style Transfer Using CycleGANs 2020 / MIG
Fully Automatic Generation of Anatomical Face Simulation Models 2015 / SCA

Keywords

spacetime editing facial animation retargeting movement matching poisson equation blendshape model specific prior velocity domain boundary conditions pca prior temporal coherence

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 →