GAN-based Reactive Motion Synthesis with Class-aware Discriminators for Human-human Interaction

qianhui men, hubert p. h. shum, edmond s. l. ho and howard leung
Computers and Graphics (C&G), 2022

Impact Factor: 1.821# Citation: 2##

GAN-based Reactive Motion Synthesis with Class-aware Discriminators for Human-human Interaction
# Impact factors from the Journal Citation Reports 2021
## Citation counts from Google Scholar as of 2022

Abstract

Creating realistic characters that can react to the users' or another character's movement can benefit computer graphics, games and virtual reality hugely. However, synthesizing such reactive motions in human-human interactions is a challenging task due to the many different ways two humans can interact. While there are a number of successful researches in adapting the generative adversarial network (GAN) in synthesizing single human actions, there are very few on modelling human-human interactions. In this paper, we propose a semi-supervised GAN system that synthesizes the reactive motion of a character given the active motion from another character. Our key insights are two-fold. First, to effectively encode the complicated spatial-temporal information of a human motion, we empower the generator with a part-based long short-term memory (LSTM) module, such that the temporal movement of different limbs can be effectively modelled. We further include an attention module such that the temporal significance of the interaction can be learned, which enhances the temporal alignment of the active-reactive motion pair. Second, as the reactive motion of different types of interactions can be significantly different, we introduce a discriminator that not only tells if the generated movement is realistic or not, but also tells the class label of the interaction. This allows the use of such labels in supervising the training of the generator. We experiment with the SBU and the HHOI datasets. The high quality of the synthetic motion demonstrates the effective design of our generator, and the discriminability of the synthesis also demonstrates the strength of our discriminator.

Downloads

YouTube

Citations

BibTeX

@article{men22gan,
 author={Men, Qianhui and Shum, Hubert P. H. and Ho, Edmond S. L. and Leung, Howard},
 journal={Computers and Graphics},
 title={GAN-based Reactive Motion Synthesis with Class-aware Discriminators for Human-human Interaction},
 year={2022},
 numpages={12},
 doi={10.1016/j.cag.2021.09.014},
 issn={0097-8493},
 publisher={Elsevier},
}

RIS

TY  - JOUR
AU  - Men, Qianhui
AU  - Shum, Hubert P. H.
AU  - Ho, Edmond S. L.
AU  - Leung, Howard
T2  - Computers and Graphics
TI  - GAN-based Reactive Motion Synthesis with Class-aware Discriminators for Human-human Interaction
PY  - 2022
DO  - 10.1016/j.cag.2021.09.014
SN  - 0097-8493
PB  - Elsevier
ER  - 

Plain Text

Qianhui Men, Hubert P. H. Shum, Edmond S. L. Ho and Howard Leung, "GAN-based Reactive Motion Synthesis with Class-aware Discriminators for Human-human Interaction," Computers and Graphics, Elsevier, 2022.

Similar Research

Qianhui Men, Edmond S. L. Ho, Hubert P. H. Shum and Howard Leung, "A Quadruple Diffusion Convolutional Recurrent Network for Human Motion Prediction", IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2021
He Wang, Edmond S. L. Ho, Hubert P. H. Shum and Zhanxing Zhu, "Spatio-temporal Manifold Learning for Human Motions via Long-horizon Modeling", IEEE Transactions on Visualization and Computer Graphics (TVCG), 2021
Qianhui Men, Howard Leung, Edmond S. L. Ho and Hubert P. H. Shum, "A Two-Stream Recurrent Network for Skeleton-Based Human Interaction Recognition", Proceedings of the 2020 International Conference on Pattern Recognition (ICPR), 2020

 

 
 

Last updated on 24 September 2022, RSS Feeds