GAN-based reactive motion synthesis with class-aware discriminators for human-human interaction

Men, Qianhui, Shum, Hubert P.H., Ho, Edmond S.L. and Leung, Howard (2021) GAN-based reactive motion synthesis with class-aware discriminators for human-human interaction. Computers and Graphics. ISSN 0097-8493 (In Press)

[img] Text
C_G_Reactive_Motion_Synthesis.pdf - Accepted Version
Restricted to Repository staff only until 9 October 2022.
Available under License Creative Commons Attribution Non-commercial No Derivatives 4.0.

Download (5MB) | Request a copy
Official URL: https://doi.org/10.1016/j.cag.2021.09.014

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.

Item Type: Article
Uncontrolled Keywords: Generative adversarial network, Attention, Reactive motion synthesis
Subjects: G400 Computer Science
Department: Faculties > Engineering and Environment > Computer and Information Sciences
Depositing User: John Coen
Date Deposited: 12 Oct 2021 11:05
Last Modified: 12 Oct 2021 11:15
URI: http://nrl.northumbria.ac.uk/id/eprint/47465

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics