A Recurrent Variational Autoencoder for Human Motion Synthesis
Ikhsanul Habibie, Daniel Holden, Jonathan Schwarz, Joe Yearsley and Taku Komura
Abstract
We propose a novel generative model of human motion that can be trained using a
large motion capture dataset, and allows users to produce animations from high-level
control signals. As previous architectures struggle to predict motions far into the future
due to the inherent ambiguity, we argue that a user-provided control signal is desirable
for animators and greatly reduces the predictive error for long sequences. Thus, we
formulate a framework which explicitly introduces an encoding of control signals into
a variational inference framework trained to learn the manifold of human motion. As
part of this framework, we formulate a prior on the latent space, which allows us to
generate high-quality motion without providing frames from an existing sequence. We
further model the sequential nature of the task by combining samples from a variational
approximation to the intractable posterior with the control signal through a recurrent
neural network (RNN) that synthesizes the motion. We show that our system can predict
the movements of the human body over long horizons more accurately than state-of-the-art methods.
Session
Posters
Files
Paper (PDF)
Supplementary (PDF)
DOI
10.5244/C.31.119
https://dx.doi.org/10.5244/C.31.119
Citation
Ikhsanul Habibie, Daniel Holden, Jonathan Schwarz, Joe Yearsley and Taku Komura. A Recurrent Variational Autoencoder for Human Motion Synthesis. In T.K. Kim, S. Zafeiriou, G. Brostow and K. Mikolajczyk, editors, Proceedings of the British Machine Vision Conference (BMVC), pages 119.1-119.12. BMVA Press, September 2017.
Bibtex
@inproceedings{BMVC2017_119,
title={A Recurrent Variational Autoencoder for Human Motion Synthesis},
author={Ikhsanul Habibie, Daniel Holden, Jonathan Schwarz, Joe Yearsley and Taku Komura},
year={2017},
month={September},
pages={119.1-119.12},
articleno={119},
numpages={12},
booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
publisher={BMVA Press},
editor={Tae-Kyun Kim, Stefanos Zafeiriou, Gabriel Brostow and Krystian Mikolajczyk},
doi={10.5244/C.31.119},
isbn={1-901725-60-X},
url={https://dx.doi.org/10.5244/C.31.119}
}