A Majorization-Minimization Based Method for Nonconvex Inverse Rig Problems in Facial Animation: Algorithm Derivation

TL;DR

This paper introduces a novel Majorization-Minimization based algorithm for nonconvex inverse rig problems in facial animation, enhancing detail and sparsity in face reconstruction while maintaining computational efficiency.

Contribution

It develops a quadratic corrective term-based method that improves accuracy and sparsity in inverse rig problems, with an iterative algorithm suitable for parallelization.

Findings

Outperforms state-of-the-art methods in accuracy and detail

Produces sparser weight vectors, reducing manual correction effort

Enables parallel computation within each iteration

Abstract

Automated methods for facial animation are a necessary tool in the modern industry since the standard blendshape head models consist of hundreds of controllers and a manual approach is painfully slow. Different solutions have been proposed that produce output in real-time or generalize well for different face topologies. However, all these prior works consider a linear approximation of the blendshape function and hence do not provide a high-enough level of details for modern realistic human face reconstruction. We build a method for solving the inverse rig in blendshape animation using quadratic corrective terms, which increase accuracy. At the same time, due to the proposed construction of the objective function, it yields a sparser estimated weight vector compared to the state-of-the-art methods. The former feature means lower demand for subsequent manual corrections of the solution, while the latter indicates that the manual modifications are also easier to include. Our algorithm is iterative and employs a Majorization Minimization paradigm to cope with the increased complexity produced by adding the corrective terms. The surrogate function is easy to solve and allows for further parallelization on the component level within each iteration. This paper is complementary to an accompanying paper, Rackovi\'c et al. (2023), where we provide detailed experimental results and discussion, including highly-realistic animation data, and show a clear superiority of the results compared to the state-of-the-art methods.