EUVIMEDEUVIMED entdecken
Crossref

GaussianHeads: End-to-End Learning of Drivable Gaussian Head Avatars from Coarse-to-fine Representations

Kartik Teotia, Hyeongwoo Kim, Pablo Garrido, Marc Habermann, Mohamed Elgharib, Christian Theobalt

ACM Transactions on Graphics · 19.12.2024 · 43 (6) · 1-12

DOI: 10.1145/3687927 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Graphics, online erschienen am 19.11.2024. Verfasst von Kartik Teotia und 5 weiteren Autor:innen. Die Arbeit wurde bisher 24-mal zitiert (Crossref) und nennt 62 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Real-time rendering of human head avatars is a cornerstone of many computer graphics applications, such as augmented reality, video games, and films, to name a few. Recent approaches address this challenge with computationally efficient geometry primitives in a carefully calibrated multi-view setup. Albeit producing photorealistic head renderings, they often fail to represent complex motion changes, such as the mouth interior and strongly varying head poses. We propose a new method to generate highly dynamic and deformable human head avatars from multi-view imagery in real time. At the core of our method is a hierarchical representation of head models that can capture the complex dynamics of facial expressions and head movements. First, with rich facial features extracted from raw input frames, we learn to deform the coarse facial geometry of the template mesh. We then initialize 3D Gaussians on the deformed surface and refine their positions in a fine step. We train this coarse-to-fine facial avatar model along with the head pose as learnable parameters in an end-to-end framework. This enables not only controllable facial animation via video inputs but also high-fidelity novel view synthesis of challenging facial expressions, such as tongue deformations and fine-grained teeth structure under large motion changes. Moreover, it encourages the learned head avatar to generalize towards new facial expressions and head poses at inference time. We demonstrate the performance of our method with comparisons against the related methods on different datasets, spanning challenging facial expression sequences across multiple identities. We also show the potential application of our approach by demonstrating a cross-identity facial performance transfer application. We make the code available on our project page.

Zitieren

APA

Teotia, K., Kim, H., Garrido, P., Habermann, M., Elgharib, M., & Theobalt, C. (2024). GaussianHeads: End-to-End Learning of Drivable Gaussian Head Avatars from Coarse-to-fine Representations. ACM Transactions on Graphics, 43(6), 1-12. https://doi.org/10.1145/3687927

Vancouver

Teotia K, Kim H, Garrido P, Habermann M, Elgharib M, Theobalt C. GaussianHeads: End-to-End Learning of Drivable Gaussian Head Avatars from Coarse-to-fine Representations. ACM Transactions on Graphics. 2024;43(6):1-12. doi:10.1145/3687927

BibTeX
@article{Teotia2024,
  author = {Teotia, Kartik and Kim, Hyeongwoo and Garrido, Pablo and Habermann, Marc and Elgharib, Mohamed and Theobalt, Christian},
  title = {GaussianHeads: End-to-End Learning of Drivable Gaussian Head Avatars from Coarse-to-fine Representations},
  journal = {ACM Transactions on Graphics},
  year = {2024},
  volume = {43},
  number = {6},
  pages = {1--12},
  doi = {10.1145/3687927}
}
Kostenlos starten →