EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Categorical Codebook Matching for Embodied Character Controllers

Sebastian Starke, Paul Starke, Nicky He, Taku Komura, Yuting Ye

ACM Transactions on Graphics · 19.07.2024 · 43 (4) · 1-14

DOI: 10.1145/3658209 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Graphics, online erschienen am 19.07.2024. Verfasst von Sebastian Starke und 4 weiteren Autor:innen. Die Arbeit wurde bisher 30-mal zitiert (Crossref) und nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Translating motions from a real user onto a virtual embodied avatar is a key challenge for character animation in the metaverse. In this work, we present a novel generative framework that enables mapping from a set of sparse sensor signals to a full body avatar motion in real-time while faithfully preserving the motion context of the user. In contrast to existing techniques that require training a motion prior and its mapping from control to motion separately, our framework is able to learn the motion manifold as well as how to sample from it at the same time in an end-to-end manner. To achieve that, we introduce a technique called codebook matching which matches the probability distribution between two categorical codebooks for the inputs and outputs for synthesizing the character motions. We demonstrate this technique can successfully handle ambiguity in motion generation and produce high quality character controllers from unstructured motion capture data. Our method is especially useful for interactive applications like virtual reality or video games where high accuracy and responsiveness are needed.

Zitieren

APA

Starke, S., Starke, P., He, N., Komura, T., & Ye, Y. (2024). Categorical Codebook Matching for Embodied Character Controllers. ACM Transactions on Graphics, 43(4), 1-14. https://doi.org/10.1145/3658209

Vancouver

Starke S, Starke P, He N, Komura T, Ye Y. Categorical Codebook Matching for Embodied Character Controllers. ACM Transactions on Graphics. 2024;43(4):1-14. doi:10.1145/3658209

BibTeX
@article{Starke2024,
  author = {Starke, Sebastian and Starke, Paul and He, Nicky and Komura, Taku and Ye, Yuting},
  title = {Categorical Codebook Matching for Embodied Character Controllers},
  journal = {ACM Transactions on Graphics},
  year = {2024},
  volume = {43},
  number = {4},
  pages = {1--14},
  doi = {10.1145/3658209}
}
Kostenlos starten →