← Search

Xuanchen Li

2 accepted papers

2025

Towards High-fidelity 3D Talking Avatar with Personalized Dynamic Texture

CVPR 2025poster

Significant progress has been made for speech-driven 3D face animation, but most works focus on learning the motion of mesh/geometry, ignoring the impact of dynamic texture. In this work, we reveal that dynamic texture plays a key role in rendering high-fidelity talking avatars, and introduce a high…

2024

Topo4D: Topology-Preserving Gaussian Splatting for High-Fidelity 4D Head Capture

ECCV 2024poster

"Recent significant advances in high-quality face reconstruction have been made, but challenges remain in 4D face asset reconstruction. 4D head capture aims to generate dynamic topological meshes and corresponding texture maps from videos, which is widely utilized in movies and games for its ability…