Probabilistic Character Motion Synthesis using a Hierarchical Deep Latent Variable Model

Abstract

We present a probabilistic framework to generate character animations based on weak control signals, such that the synthesized motions are realistic while retaining the stochastic nature of human movement. The proposed architecture, which is designed as a hierarchical recurrent model, maps each sub-sequence of motions into a stochastic latent code using a variational autoencoder extended over the temporal domain. We also propose an objective function which respects the impact of each joint on the pose and compares the joint angles based on angular distance. We use two novel quantitative protocols and human qualitative assessment to demonstrate the ability of our model to generate convincing and diverse periodic and non-periodic motion sequences without the need for strong control signals.

References in corpus (12)

• Auto-Encoding Variational Bayes
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• An Introduction to Variational Autoencoders
• NICE: Non-linear Independent Components Estimation
• Variational Inference with Normalizing Flows
• Normalizing Flows: An Introduction and Review of Current Methods
• DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills
• A Recurrent Latent Variable Model for Sequential Data
• Normalizing Flows for Probabilistic Modeling and Inference
• Character Controllers Using Motion VAEs
• Unpaired Motion Style Transfer from Video to Animation
• MoVi: A Large Multipurpose Motion and Video Dataset

Cited by in corpus (5)

• MoVi: A Large Multipurpose Motion and Video Dataset
• A Survey on Deep Learning for Skeleton-Based Human Animation
• Rhythm is a Dancer: Music-Driven Motion Synthesis with Global Structure
• A causal convolutional neural network for multi-subject motion modeling and generation
• Graph-based Normalizing Flow for Human Motion Generation and Reconstruction