Skip to content

← ArchivePaper2024

Refined Inverse Rigging: A Balanced Approach to High-fidelity Blendshape Animation

Stevo Rackovic, Dusan Jakovetic, Claudia Soares

SIGGRAPH AsiaAcademic3 citesFacialRigging

Inverse rig solver combines l1 sparsity and temporal roughness penalties to produce high-fidelity, smooth blendshape weight sequences.

Abstract

In this paper, we present an advanced approach to solving the inverse rig problem in blendshape animation, using high-quality corrective blendshapes. Our algorithm focuses on three key areas: ensuring high data fidelity in reconstructed meshes, achieving greater sparsity in weight distributions, and facilitating smoother frame-to-frame transitions. While the incorporation of corrective terms is a known practice, our method differentiates itself by employing a unique combination of l1 norm regularization for sparsity and a temporal smoothness constraint through roughness penalty, focusing on the sum of second differences in consecutive frame weights. A significant innovation in our approach is the temporal decoupling of blendshapes, which permits simultaneous optimization across entire animation sequences. This feature sets our work apart from existing methods and contributes to a more efficient and effective solution. Our algorithm exhibits a marked improvement in maintaining data fidelity and ensuring smooth frame transitions when compared to prior approaches that either lack smoothness regularization or rely solely on linear blendshape models. In addition to superior mesh resemblance and smoothness, our method offers practical benefits, including reduced computational complexity and execution time, achieved through a novel parallelization strategy using clustering methods.

How to read this

Category
Method: inverse-rig solver for blendshape animation
Contributions
  • An inverse-rig solver using high-quality corrective blendshapes that targets data fidelity, weight sparsity, and smooth frame-to-frame transitions
  • A combination of l1 regularization for sparsity with a temporal roughness penalty (sum of second differences across frames)
  • Temporal decoupling of blendshapes allowing simultaneous optimization over an entire sequence
Context
An optimization-based inverse-rig method extending the inverse rig-mapping line of work, building on Learning an Inverse Rig Mapping for Character Animation (Holden 2015).Builds on: Learning an Inverse Rig Mapping for Character Animation
Correctness
Reports improved fidelity and smoother transitions versus methods lacking smoothness regularization or using linear-only blendshapes; gains depend on having high-quality corrective blendshapes, which a reader should treat as a precondition.
Clarity
Mathematically framed; a first pass conveys the three objectives, but the regularization terms and decoupling need a second pass.
How to read it
First pass for the three goals (fidelity, sparsity, smoothness) and the l1-plus-roughness recipe; second pass on the temporal-decoupling formulation if you implement the solver.

Builds on

Built upon by

Nothing yet.

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 →