Efficient 3D Neural Head Avatar with Vertex-Anchored Hash Table Blendshapes for Real-Time Rendering
We propose a novel 3D neural head avatar representation that achieves real-time rendering while maintaining high-quality and fine-grained controllability. The key idea is to attach multiple small hash tables as "local blendshapes" to each vertex of an underlying 3D face model, which are then linearly merged with expression-dependent weights to produce expression-specific embeddings for efficient neural radiance field decoding.