Probabilistic Character Motion Synthesis using a Hierarchical Deep Latent Variable Model. (24th November 2020)

• Record Type: Journal Article
• Authors: Ghorbani, S.; Wloka, C.; Etemad, A.; Brubaker, M. A.; Troje, N. F.
• Is Part Of: Computer graphics forum. Volume 39:Number 8(2020)
• Page Start: 225
• Page End: 239
• Publication Date: 2020-11-24
• Subjects: CCS Concepts -- Computing methodologies → Animation -- Machine learning approaches; Computer graphics -- Periodicals; 006.605
• DOI: 10.1111/cgf.14116
• Languages: English
• ISSNs: 0167-7055

Abstract

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.