Efficient stochastic human motion prediction via consistency model

Renhao Pan

doi:10.1117/12.3055738

9 January 2025 Efficient stochastic human motion prediction via consistency model

Renhao Pan

Author Affiliations +

Proceedings Volume 13486, Fourth International Conference on Computer Vision, Application, and Algorithm (CVAA 2024); 1348639 (2025) https://doi.org/10.1117/12.3055738
Event: Fourth International Conference on Computer Vision, Application, and Algorithm (CVAA 2024), 2024, Chengdu, China

Abstract

Diffusion models have recently proven successful in stochastic human motion prediction. Despite their excellent generative performance, they are difficult to predict in real-time because the multi-step sampling mechanism involves tens or hundreds of iterations of repetitive function evaluation. To address this issue, we introduce the Motion Consistency Model (MotionCM) to alleviate the computational and time consumption of the iterative inference process. It applies a diffusion pipeline to the low-frequency domain processed by discrete cosine transformation(DCT), alleviating the computational burden for each function evaluation. The predictive efficiency of the motion diffusion model in stochastic human motion is further improved by employing a one-step (or several-step) inference via maintaining consistency of the outputs over the trajectory of PF-ODE. Extensive experiments on two benchmark datasets show that the proposed model achieves state-of-the-art performance at less than 10% of the time cost.

(2025) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Renhao Pan "Efficient stochastic human motion prediction via consistency model", Proc. SPIE 13486, Fourth International Conference on Computer Vision, Application, and Algorithm (CVAA 2024), 1348639 (9 January 2025); https://doi.org/10.1117/12.3055738

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

;

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE