DiffusionTalker: Personalization and Acceleration for Speech-Driven 3D Face

doi:doi:10.57702/am9oj3nk

DiffusionTalker: Personalization and Acceleration for Speech-Driven 3D Face

Speech-driven 3D facial animation has been an attractive task in both academia and industry. Traditional methods mostly focus on learning a deterministic mapping from speech to animation. Recent approaches start to consider the non-deterministic fact of speech-driven 3D face animation and employ the diffusion model for the task.

BibTex:

@dataset{Peng_Chen_and_Xiaobao_Wei_and_Ming_Lu_and_Yitong_Zhu_and_Naiming_Yao_and_Xingyu_Xiao_and_Hui_Chen_2024,
    abstract = {Speech-driven 3D facial animation has been an attractive task in both academia and industry. Traditional methods mostly focus on learning a deterministic mapping from speech to animation. Recent approaches start to consider the non-deterministic fact of speech-driven 3D face animation and employ the diffusion model for the task.},
    author = {Peng Chen and Xiaobao Wei and Ming Lu and Yitong Zhu and Naiming Yao and Xingyu Xiao and Hui Chen},
    doi = {10.57702/am9oj3nk},
    institution = {No Organization},
    keyword = {'Acceleration', 'Diffusion Model', 'Personalization', 'Speech-Driven 3D Facial Animation'},
    month = {dec},
    publisher = {TIB},
    title = {DiffusionTalker: Personalization and Acceleration for Speech-Driven 3D Face},
    url = {https://service.tib.eu/ldmservice/dataset/diffusiontalker--personalization-and-acceleration-for-speech-driven-3d-face},
    year = {2024}
}