Data-driven modelling and synthesis of motion is an active research area with applications that include animation, games, and social robotics. This paper introduces a new class of probabilistic, generative, and controllable motion-data models based on normalising flows. Models of this kind can describe highly complex distributions, yet can be trained efficiently using exact maximum likelihood, unlike GANs or VAEs. Our proposed model is autoregressive and uses LSTMs to enable arbitrarily long time-dependencies. Importantly, is is also causal, meaning that each pose in the output sequence is generated without access to poses or control inputs from future time steps; this absence of algorithmic latency is important for interactive applications with real-time motion control. The approach can in principle be applied to any type of motion since it does not make restrictive, task-specific assumptions regarding the motion or the character morphology. We evaluate the models on motion-capture datasets of human and quadruped locomotion. Objective and subjective results show that randomly-sampled motion from the proposed method outperforms task-agnostic baselines and attains a motion quality close to recorded motion capture. ; QC 20200929 ; VR proj. 2018-05409 (StyleBot) ; SSF no. RIT15-0107 (EACare) ; Wallenberg AI, Autonomous Systems and Software Program (WASP)


    Access

    Download


    Export, share and cite



    Title :

    MoGlow: Probabilistic and controllable motion synthesis using normalising flows


    Contributors:

    Publication date :

    2020-01-01


    Remarks:

    Scopus 2-s2.0-85096681707



    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    Classification :

    DDC:    629



    Method for normalising information from traffic data

    GAME ADAM | European Patent Office | 2015

    Free access


    MOTION SYSTEM WITH CONTROLLABLE ROTATION RANGE

    DENG MEIMEI | European Patent Office | 2024

    Free access

    Probabilistic Parameter-Free Motion Detection

    Veit, T. / Cao, F. / Bouthemy, P. et al. | British Library Conference Proceedings | 2004


    Probabilistic parameter-free motion detection

    Veit, T. / Cao, F. / Bouthemy, P. | IEEE | 2004