Unifying Human Motion Synthesis and Style Transfer with Denoising Diffusion Probabilistic Models

Ziyi Chang, Edmund J. C. Findlay, Haozheng Zhang and Hubert P. H. Shum
Proceedings of the 2023 International Conference on Computer Graphics Theory and Applications (GRAPP), 2023

Unifying Human Motion Synthesis and Style Transfer with Denoising Diffusion Probabilistic Models

Abstract

Generating realistic motions for digital humans is a core but challenging part of computer animations and games, as human motions are both diverse in content and rich in styles. While the latest deep learning approaches have made significant advancements in this domain, they mostly consider motion synthesis and style manipulation as two separate problems. This is mainly due to the challenge of learning both motion contents that account for the inter-class behaviour and styles that account for the intra-class behaviour effectively in a common representation. To tackle this challenge, we propose a denoising diffusion probabilistic model solution for styled motion synthesis. As diffusion models have a high capacity brought by the injection of stochasticity, we can represent both inter-class motion content and intra-class style behaviour in the same latent. This results in an integrated, end-to-end trained pipeline that facilitates the generation of optimal motion and exploration of content-style coupled latent space. To achieve high-quality results, we design a multi-task architecture of diffusion model that strategically generates aspects of human motions for local guidance. We also design adversarial and physical regulations for global guidance. We demonstrate superior performance with quantitative and qualitative results and validate the effectiveness of our multi-task architecture.

Downloads

YouTube

Citations

BibTeX

@inproceedings{chang23unifying,
 author={Chang, Ziyi and Findlay, Edmund J. C. and Zhang, Haozheng and Shum, Hubert P. H.},
 booktitle={Proceedings of the 2023 International Conference on Computer Graphics Theory and Applications},
 series={GRAPP '23},
 title={Unifying Human Motion Synthesis and Style Transfer with Denoising Diffusion Probabilistic Models},
 year={2023},
 month={2},
 pages={64--74},
 numpages={11},
 doi={10.5220/0011631000003417},
 issn={2184-4321},
 isbn={978-989-758-634-7},
 publisher={SciTePress},
 location={Lisbon, Portugal},
}

RIS

TY  - CONF
AU  - Chang, Ziyi
AU  - Findlay, Edmund J. C.
AU  - Zhang, Haozheng
AU  - Shum, Hubert P. H.
T2  - Proceedings of the 2023 International Conference on Computer Graphics Theory and Applications
TI  - Unifying Human Motion Synthesis and Style Transfer with Denoising Diffusion Probabilistic Models
PY  - 2023
Y1  - 2 2023
SP  - 64
EP  - 74
DO  - 10.5220/0011631000003417
SN  - 2184-4321
PB  - SciTePress
ER  - 

Plain Text

Ziyi Chang, Edmund J. C. Findlay, Haozheng Zhang and Hubert P. H. Shum, "Unifying Human Motion Synthesis and Style Transfer with Denoising Diffusion Probabilistic Models," in GRAPP '23: Proceedings of the 2023 International Conference on Computer Graphics Theory and Applications, pp. 64-74, Lisbon, Portugal, SciTePress, Feb 2023.

Supporting Grants

Similar Research

Edmund J. C. Findlay, Haozheng Zhang, Ziyi Chang and Hubert P. H. Shum, "Denoising Diffusion Probabilistic Models for Styled Walking Synthesis", Proceedings of the 2022 ACM SIGGRAPH Conference on Motion, Interaction and Games (MIG) Posters, 2022
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
Edmond S. L. Ho, Hubert P. H. Shum, He Wang and Li Yi, "Synthesizing Motion with Relative Emotion Strength", Proceedings of the 2017 ACM SIGGRAPH Asia Workshop on Data-Driven Animation Techniques (D2AT), 2017
Liuyang Zhou, Lifeng Shang, Hubert P. H. Shum and Howard Leung, "Human Motion Variation Synthesis with Multivariate Gaussian Processes", Computer Animation and Virtual Worlds (CAVW) - Proceedings of the 2014 International Conference on Computer Animation and Social Agents (CASA), 2014
Hubert P. H. Shum, Ludovic Hoyet, Edmond S. L. Ho, Taku Komura and Franck Multon, "Preparation Behaviour Synthesis with Reinforcement Learning", Proceedings of the 2013 International Conference on Computer Animation and Social Agents (CASA), 2013
Hubert P. H. Shum, Ludovic Hoyet, Edmond S. L. Ho, Taku Komura and Franck Multon, "Natural Preparation Behavior Synthesis", Computer Animation and Virtual Worlds (CAVW), 2013
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
Hubert P. H. Shum, Taku Komura and Pranjul Yadav, "Angular Momentum Guided Motion Concatenation", Computer Animation and Virtual Worlds (CAVW) - Proceedings of the 2009 International Conference on Computer Animation and Social Agents (CASA), 2009

 

 

Last updated on 4 June 2024
RSS Feed