Skip to main content

Research Repository

Advanced Search

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

Chang, Ziyi; Findlay, Edmund J.C.; Zhang, Haozheng; Shum, Hubert P.H.

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


Authors

Ziyi Chang ziyi.chang@durham.ac.uk
PGR Student Doctor of Philosophy

Edmund J.C. Findlay

Haozheng Zhang haozheng.zhang@durham.ac.uk
PGR Student Doctor of Philosophy



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.

Citation

Chang, Z., Findlay, E. J., Zhang, H., & Shum, H. P. (2023). Unifying Human Motion Synthesis and Style Transfer with Denoising Diffusion Probabilistic Models. In Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - GRAPP (64-74). https://doi.org/10.5220/0011631000003417

Conference Name GRAPP 2023: 2023 International Conference on Computer Graphics Theory and Applications
Conference Location Lisbon, Portugal
Start Date Feb 19, 2023
End Date Feb 21, 2023
Acceptance Date Dec 6, 2022
Publication Date 2023
Deposit Date Dec 12, 2022
Publicly Available Date Mar 29, 2024
Pages 64-74
Series ISSN 2184-4321
Book Title Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - GRAPP
ISBN 9789897586347
DOI https://doi.org/10.5220/0011631000003417
Public URL https://durham-repository.worktribe.com/output/1134303

Files





You might also like



Downloadable Citations