Pose Representations for Deep Skeletal Animation

TL;DR

This paper introduces a dual quaternion-based pose representation for deep skeletal animation that better captures motion nuances, reduces artifacts, and enables training across diverse skeletons without retargeting.

Contribution

It proposes a novel dual quaternion-based pose encoding that improves motion fidelity and robustness in deep character animation models.

Findings

Overcomes common motion artifacts

Enables training on diverse skeletons without retargeting

Produces smooth and natural poses

Abstract

Data-driven character animation techniques rely on the existence of a properly established model of motion, capable of describing its rich context. However, commonly used motion representations often fail to accurately encode the full articulation of motion, or present artifacts. In this work, we address the fundamental problem of finding a robust pose representation for motion modeling, suitable for deep character animation, one that can better constrain poses and faithfully capture nuances correlated with skeletal characteristics. Our representation is based on dual quaternions, the mathematical abstractions with well-defined operations, which simultaneously encode rotational and positional orientation, enabling a hierarchy-aware encoding, centered around the root. We demonstrate that our representation overcomes common motion artifacts, and assess its performance compared to other popular representations. We conduct an ablation study to evaluate the impact of various losses that can be incorporated during learning. Leveraging the fact that our representation implicitly encodes skeletal motion attributes, we train a network on a dataset comprising of skeletons with different proportions, without the need to retarget them first to a universal skeleton, which causes subtle motion elements to be missed. We show that smooth and natural poses can be achieved, paving the way for fascinating applications.