Paper ID: 2301.09567

Rig Inversion by Training a Differentiable Rig Function

Mathieu Marquis Bolduc, Hau Nghiep Phan

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.

Submitted: Jan 11, 2023