Style-based inverse kinematics

TLDR

The model is a probability distribution over all possible human poses. The paper introduces a style‑based inverse‑kinematics system that learns human poses, can interpolate between styles, and replaces conventional IK in animation and vision. The system employs a Scaled Gaussian Process Latent Variable Model to learn this distribution, enabling real‑time generation of the most likely pose that satisfies given constraints without manual tuning. Training on varied data yields distinct IK styles, and the learned model automatically generates poses that favor the training distribution, allowing style interpolation and replacement of conventional IK.

Abstract

This paper presents an inverse kinematics system based on a learned model of human poses. Given a set of constraints, our system can produce the most likely pose satisfying those constraints, in real-time. Training the model on different input data leads to different styles of IK. The model is represented as a probability distribution over the space of all possible poses. This means that our IK system can generate any pose, but prefers poses that are most similar to the space of poses in the training data. We represent the probability with a novel model called a Scaled Gaussian Process Latent Variable Model. The parameters of the model are all learned automatically; no manual tuning is required for the learning component of the system. We additionally describe a novel procedure for interpolating between styles.Our style-based IK can replace conventional IK, wherever it is used in computer animation and computer vision. We demonstrate our system in the context of a number of applications: interactive character posing, trajectory keyframing, real-time motion capture with missing markers, and posing from a 2D image.