Rig Inversion by Training a Differentiable Rig Function
This addresses rig inversion for computer graphics and animation, but appears incremental as it builds on existing deep learning approaches.
The paper tackles the problem of rig inversion, which involves finding rig parameters that best approximate a given input mesh, by training a multi-layer perceptron to create a differentiable rig function and then using it to train a deep learning model for inversion.
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.