elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Can We Use Diffusion Probabilistic Models for 3D Motion Prediction?

Ahn, Hyemin and Mascaro, Esteve Valls and Lee, Dongheui (2023) Can We Use Diffusion Probabilistic Models for 3D Motion Prediction? In: 2023 IEEE International Conference on Robotics and Automation, ICRA 2023, pp. 9837-9843. IEEE. 2023 IEEE International Conference on Robotics and Automation, 2023-05-29 - 2023-06-02, London, UK. doi: 10.1109/ICRA48891.2023.10160722. ISBN 979-835032365-8. ISSN 1050-4729.

[img] PDF
1MB

Official URL: https://ieeexplore.ieee.org/document/10160722

Abstract

After many researchers observed fruitfulness from the recent diffusion probabilistic model, its effectiveness in image generation is actively studied these days. In this paper, our objective is to evaluate the potential of diffusion probabilistic models for 3D human motion-related tasks. To this end, this pa-per presents a study of employing diffusion probabilistic models to predict future 3D human motion(s) from the previously observed motion. Based on the Human 3.6M and HumanEva-I datasets, our results show that diffusion probabilistic models are competitive for both single (deterministic) and multiple (stochastic) 3D motion prediction tasks, after finishing a single training process. In addition, we find out that diffusion probabilistic models can offer an attractive compromise, since they can strike the right balance between the likelihood and diversity of the predicted future motions. Our code is publicly available on the project website: https://sites.google.com/view/diffusion-motion-prediction.

Item URL in elib:https://elib.dlr.de/197486/
Document Type:Conference or Workshop Item (Speech)
Title:Can We Use Diffusion Probabilistic Models for 3D Motion Prediction?
Authors:
AuthorsInstitution or Email of AuthorsAuthor's ORCID iDORCID Put Code
Ahn, HyeminUNSPECIFIEDhttps://orcid.org/0000-0001-8081-6023UNSPECIFIED
Mascaro, Esteve VallsTU WienUNSPECIFIEDUNSPECIFIED
Lee, DongheuiUNSPECIFIEDhttps://orcid.org/0000-0003-1897-7664UNSPECIFIED
Date:4 July 2023
Journal or Publication Title:2023 IEEE International Conference on Robotics and Automation, ICRA 2023
Refereed publication:Yes
Open Access:Yes
Gold Open Access:No
In SCOPUS:Yes
In ISI Web of Science:No
DOI:10.1109/ICRA48891.2023.10160722
Page Range:pp. 9837-9843
Publisher:IEEE
ISSN:1050-4729
ISBN:979-835032365-8
Status:Published
Keywords:Diffusion Probabilistic Models
Event Title:2023 IEEE International Conference on Robotics and Automation
Event Location:London, UK
Event Type:international Conference
Event Start Date:29 May 2023
Event End Date:2 June 2023
Organizer:IEEE
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Robotics
DLR - Research area:Raumfahrt
DLR - Program:R RO - Robotics
DLR - Research theme (Project):R - Basic Technologies [RO]
Location: Oberpfaffenhofen
Institutes and Institutions:Institute of Robotics and Mechatronics (since 2013)
Deposited By: Strobl, Dr.-Ing. Klaus H.
Deposited On:22 Sep 2023 12:57
Last Modified:11 Mar 2025 17:11

Repository Staff Only: item control page

Browse
Search
Help & Contact
Information
OpenAIRE Validator logo electronic library is running on EPrints 3.3.12
Website and database design: Copyright © German Aerospace Center (DLR). All rights reserved.