EUVIMEDEUVIMED entdecken
Crossref

Text2Avatar: Articulated 3D Avatar Creation With Text Instructions

Yong-Hoon Kwon, Ju Hong Yoon, Min-Gyu Park

IEEE Transactions on Multimedia · 2025 · 27 · 3797-3806

DOI: 10.1109/tmm.2025.3535293 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Multimedia, 2025. Verfasst von Yong-Hoon Kwon und 2 weiteren Autor:innen. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 79 Literaturangaben. Gefördert von: Information and Communications Technology Planning and Evaluation, Korea Government, Rediscovery of R&D Project funded by the Ministry of Trade, Industry.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We propose a framework for creating articulated human avatars, editing their styles, and animating the human avatars from three different types of text instructions. The three types of instructions, identity, edit, and action, are fed into three models that generate, edit, and animate human avatars. Specifically, the proposed framework takes identity instruction and multi-view pose condition images to generate the images of a human using the avatar generation model. Then, the avatar can be edited with text instructions by changing the style of the images generated. We apply the Neural Radiance Field (NeRF) and Poisson reconstruction to extract a human mesh model from images and assign linear blend skinning (LBS) weights to the vertices. Finally, the action instructions can animate human avatars, where we use the off-the-shelf method to generate the motions from text instructions. Notably, our proposed method adapts the appearance of hundreds of different individuals to construct a conditionally editable avatar-generated model, allowing easy creation of 3D avatars using text instructions. We demonstrate high-fidelity 3D animatable avatar creation with text instructions on various datasets and highlight a superior performance of the proposed method compared to the previous studies.

Förderung

  • Information and Communications Technology Planning and Evaluation
  • Korea Government
  • Rediscovery of R&D Project funded by the Ministry of Trade, Industry

Zitieren

APA

Kwon, Y., Yoon, J. H., & Park, M. (2025). Text2Avatar: Articulated 3D Avatar Creation With Text Instructions. IEEE Transactions on Multimedia, 27, 3797-3806. https://doi.org/10.1109/tmm.2025.3535293

Vancouver

Kwon Y, Yoon JH, Park M. Text2Avatar: Articulated 3D Avatar Creation With Text Instructions. IEEE Transactions on Multimedia. 2025;27:3797-3806. doi:10.1109/tmm.2025.3535293

BibTeX
@article{Kwon2025,
  author = {Kwon, Yong-Hoon and Yoon, Ju Hong and Park, Min-Gyu},
  title = {Text2Avatar: Articulated 3D Avatar Creation With Text Instructions},
  journal = {IEEE Transactions on Multimedia},
  year = {2025},
  volume = {27},
  pages = {3797--3806},
  doi = {10.1109/tmm.2025.3535293}
}
Kostenlos starten →