Rig Inversion by Training a Differentiable Rig Function
Graphics
2023-01-24 v1 Artificial Intelligence
Machine Learning
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.
Cite
@article{arxiv.2301.09567,
title = {Rig Inversion by Training a Differentiable Rig Function},
author = {Mathieu Marquis Bolduc and Hau Nghiep Phan},
journal= {arXiv preprint arXiv:2301.09567},
year = {2023}
}
Comments
Presented at Siggraph Asia '22 in Daegu, South Korea