EUVIMEDEUVIMED entdecken
Crossref

Scalable Motion Style Transfer with Constrained Diffusion Generation

Wenjie Yin, Yi Yu, Hang Yin, Danica Kragic, Mårten Björkman

Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (9) · 10234-10242

DOI: 10.1609/aaai.v38i9.28889 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Wenjie Yin und 4 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Current training of motion style transfer systems relies on consistency losses across style domains to preserve contents, hindering its scalable application to a large number of domains and private data. Recent image transfer works show the potential of independent training on each domain by leveraging implicit bridging between diffusion models, with the content preservation, however, limited to simple data patterns. We address this by imposing biased sampling in backward diffusion while maintaining the domain independence in the training stage. We construct the bias from the source domain keyframes and apply them as the gradient of content constraints, yielding a framework with keyframe manifold constraint gradients (KMCGs). Our validation demonstrates the success of training separate models to transfer between as many as ten dance motion styles. Comprehensive experiments find a significant improvement in preserving motion contents in comparison to baseline and ablative diffusion-based style transfer models. In addition, we perform a human study for a subjective assessment of the quality of generated dance motions. The results validate the competitiveness of KMCGs.

Zitieren

APA

Yin, W., Yu, Y., Yin, H., Kragic, D., & Björkman, M. (2024). Scalable Motion Style Transfer with Constrained Diffusion Generation. Proceedings of the AAAI Conference on Artificial Intelligence, 38(9), 10234-10242. https://doi.org/10.1609/aaai.v38i9.28889

Vancouver

Yin W, Yu Y, Yin H, Kragic D, Björkman M. Scalable Motion Style Transfer with Constrained Diffusion Generation. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(9):10234-10242. doi:10.1609/aaai.v38i9.28889

BibTeX
@article{Yin2024,
  author = {Yin, Wenjie and Yu, Yi and Yin, Hang and Kragic, Danica and Björkman, Mårten},
  title = {Scalable Motion Style Transfer with Constrained Diffusion Generation},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2024},
  volume = {38},
  number = {9},
  pages = {10234--10242},
  doi = {10.1609/aaai.v38i9.28889}
}
Kostenlos starten →