Rig Inversion by Training a Differentiable Rig Function

Abstract

Rig inversion is the problem of creating a method that can find the rig parameter vector that best approximates a given input mesh. In this paper we propose to solve this problem by first obtaining a differentiable rig function by training a multi layer perceptron to approximate the rig function. This differentiable rig function can then be used to train a deep learning model of rig inversion.

Presented at Siggraph Asia '22 in Daegu, South Korea

References in corpus (2)

• Accurate Face Rig Approximation with Deep Differential Subspace Reconstruction
• Accurate, Interpretable, and Fast Animation: An Iterative, Sparse, and Nonconvex Approach