Pose Representations for Deep Skeletal Animation

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.

arXiv commentPresented at the ACM SIGGRAPH/Eurographics Symposium on Computer Animation, SCA'22

References in corpus (15)

• Adam: A Method for Stochastic Optimization
• OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields
• Character Controllers Using Motion VAEs
• Robust Motion In-betweening
• Skeleton-Aware Networks for Deep Motion Retargeting
• QuaterNet: A Quaternion-based Recurrent Model for Human Motion
• Unpaired Motion Style Transfer from Video to Animation
• MoGlow: Probabilistic and controllable motion synthesis using normalising flows
• MotioNet: 3D Human Motion Reconstruction from Monocular Video with Skeleton Consistency
• Learning to Generate Diverse Dance Motions with Transformer
• A Survey on Deep Learning for Skeleton-Based Human Animation
• On the Continuity of Rotation Representations in Neural Networks
• Rhythm is a Dancer: Music-Driven Motion Synthesis with Global Structure
• A Smooth Representation of Belief over SO(3) for Deep Rotation Learning with Uncertainty
• Towards Robust Direction Invariance in Character Animation

Cited by in corpus (2)

• SparsePoser: Real-time Full-body Motion Reconstruction from Sparse Data
• DragPoser: Motion Reconstruction from Variable Sparse Tracking Signals via Latent Space Optimization