FHAvatar: Fast and High-Fidelity Reconstruction of Face-and-Hair Composable 3D Head Avatar from Few Casual Captures
This addresses the challenge of accessible digital avatar creation for applications like animation and virtual reality, though it appears incremental by building on existing 3D Gaussian methods.
The paper tackles the problem of reconstructing 3D head avatars with composable face and hair components from few casual captures, achieving state-of-the-art quality within minutes while supporting real-time animation and editing.
We present FHAvatar, a novel framework for reconstructing 3D Gaussian avatars with composable face and hair components from an arbitrary number of views. Unlike previous approaches that couple facial and hair representations within a unified modeling process, we explicitly decouple two components in texture space by representing the face with planar Gaussians and the hair with strand-based Gaussians. To overcome the limitations of existing methods that rely on dense multi-view captures or costly per-identity optimization, we propose an aggregated transformer backbone to learn geometry-aware cross-view priors and head-hair structural coherence from multi-view datasets, enabling effective and efficient feature extraction and fusion from few casual captures. Extensive quantitative and qualitative experiments demonstrate that FHAvatar achieves state-of-the-art reconstruction quality from only a few observations of new identities within minutes, while supporting real-time animation, convenient hairstyle transfer, and stylized editing, broadening the accessibility and applicability of digital avatar creation.