2025/09/21 by Zhu, Tianheng, Yingfeng Yu, Liejun Wang +6
Computer Science · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #FOS: Electrical engineering #Face recognition and analysis #Human Pose and Action Recognition #Image and Video Processing (eess.IV) #Sound (cs.SD) #Speech and Audio Processing #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2509.16922
openalex publication_date 2025/09/21 · openalex created_date 2025/10/16 · openalex updated_date 2026/07/28
Audio-driven talking head generation is crucial for applications in virtual reality, digital avatars, and film production. While NeRF-based methods enable high-fidelity reconstruction, they suffer from low rendering efficiency and suboptimal audio-visual synchronization. This work presents PGSTalker, a real-time audio-driven talking head synthesis framework based on 3D Gaussian Splatting (3DGS). To improve rendering performance, we propose a pixel-aware density control strategy that adaptively allocates point density, enhancing detail in dynamic facial regions while reducing redundancy elsewhere. Additionally, we introduce a lightweight Multimodal Gated Fusion Module to effectively fuse audio and spatial features, thereby improving the accuracy of Gaussian deformation prediction. Extensive experiments on public datasets demonstrate that PGSTalker outperforms existing NeRF- and 3DGS-based approaches in rendering quality, lip-sync precision, and inference speed. Our method exhibits strong generalization capabilities and practical potential for real-world deployment.