AI RESEARCH
OMG-Avatar: One-shot Multi-LOD Gaussian Head Avatar
arXiv CS.CV
•
ArXi:2603.01506v2 Announce Type: replace We propose OMG-Avatar, a novel One-shot method that leverages a Multi-LOD (Level-of-Detail) Gaussian representation for animatable 3D head reconstruction from a single image in 0.2s. Our method enables LOD head avatar modeling using a unified model that accommodates diverse hardware capabilities and inference speed requirements. To capture both global and local facial characteristics, we employ a transformer-based architecture for global feature extraction and projection-based sampling for local feature acquisition.