Zhiwen Jiang

LMTalker: Sparse Landmark-guided Gaussian Splatting for High-fidelity Talking Head Synthesis

3D Gaussian splatting (3DGS) has demonstrated significant potential in audio-driven talking head synthesis. However, despite notable advancements in speed and fidelity, current methods still face challenges such as inaccurate lip movements and facial artifacts. To address these issues, we propose LM…