EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

VQ‐Style: Disentangling Style and Content in Motion with Residual Quantized Representations

Fatemeh Zargarbashi, Dhruv Agrawal, Jakob Buhmann, Martin Guay, Stelian Coros, Robert W. Sumner

Computer Graphics Forum · 30.04.2026

DOI: 10.1111/cgf.70377 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computer Graphics Forum, online erschienen am 30.04.2026. Verfasst von Fatemeh Zargarbashi und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Human motion data is inherently rich and complex, containing both semantic content and subtle stylistic features that are challenging to model. We propose a novel method for effective disentanglement of the style and content in human motion data to facilitate style transfer. Our approach is guided by the insight that content corresponds to coarse motion attributes while style captures the finer, expressive details. To model this hierarchy, we employ Residual Vector Quantized Variational Autoencoders (RVQ‐VAEs) to learn a coarse‐to‐fine representation of motion. We further enhance the disentanglement by integrating codebook learning with contrastive learning and a novel information leakage loss to organize the content and the style across different codebooks. We harness this disentangled representation using our simple and effective inference‐time technique Quantized Code Swapping , which enables motion style transfer without requiring any fine‐tuning for unseen styles. Our framework demonstrates strong versatility across multiple inference applications, including style transfer, style removal, and motion blending.

Zitieren

APA

Zargarbashi, F., Agrawal, D., Buhmann, J., Guay, M., Coros, S., & Sumner, R. W. (2026). VQ‐Style: Disentangling Style and Content in Motion with Residual Quantized Representations. Computer Graphics Forum. https://doi.org/10.1111/cgf.70377

Vancouver

Zargarbashi F, Agrawal D, Buhmann J, Guay M, Coros S, Sumner RW. VQ‐Style: Disentangling Style and Content in Motion with Residual Quantized Representations. Computer Graphics Forum. 2026. doi:10.1111/cgf.70377

BibTeX
@article{Zargarbashi2026,
  author = {Zargarbashi, Fatemeh and Agrawal, Dhruv and Buhmann, Jakob and Guay, Martin and Coros, Stelian and Sumner, Robert W.},
  title = {VQ‐Style: Disentangling Style and Content in Motion with Residual Quantized Representations},
  journal = {Computer Graphics Forum},
  year = {2026},
  doi = {10.1111/cgf.70377}
}
Kostenlos starten →