高技术通讯2026，Vol.36Issue(3)：221-229,9.DOI:10.3772/j.issn.1002-0470.2026.03.001
语音驱动的三维高斯人脸运动生成方法
Audio-driven 3D facial motion generation via Gaussian splatting
摘要
Abstract
With the development of digital human technology,synthesizing realistic facial motions that align with audio has become a significant research focus.Existing image-based facial motion synthesis methods are often limited to specific camera angles and struggle with accurately expressing facial details.The core issue lies in the lack of effec-tive 3D representation.To address this problem,this paper proposes an audio-driven 3D facial motion generation method via Gaussian splatting.The method first combines 3D Gaussian splatting with a parametric facial model to perform 3D modeling of dynamic facial data,establishing a relationship between the Gaussian representation and the mesh model.For motion generation,audio-driven movements are mapped to the vertex displacements on the facial model,and dynamic facial Gaussian deformation is achieved through mesh deformation.Compared to existing meth-ods,the proposed Gaussian-based facial motion generation method demonstrates superior 3D consistency and image quality,along with significantly improved generation and rendering efficiency.关键词
高斯泼溅/语音驱动/参数化人脸模型Key words
Gaussian splatting/audio-driven/parametric facial model引用本文复制引用
李小娟,陈姝宇..语音驱动的三维高斯人脸运动生成方法[J].高技术通讯,2026,36(3):221-229,9.基金项目
国家自然科学基金青年基金(62102403)资助项目. （62102403）
