AI RESEARCH
Structure-Aware Fine-Grained Gaussian Splatting for Expressive Avatar Reconstruction
arXiv CS.CV
•
ArXi:2604.09324v1 Announce Type: new Reconstructing photorealistic and topology-aware human avatars from monocular videos remains a significant challenge in the fields of computer vision and graphics. While existing 3D human avatar modeling approaches can effectively capture body motion, they often fail to accurately model fine details such as hand movements and facial expressions. To address this, we propose Structure-aware Fine-grained Gaussian Splatting (SFGS), a novel method for reconstructing expressive and coherent full-body 3D human avatars from a monocular video sequence.