Research
URHead: A Unified UV-Space Representation for Joint Mesh-3DGS Optimization in Head Avatars
arXiv:2607.22673v1 Announce Type: cross Abstract: We present URHead, a unified representation for high-fidelity and animatable head avatars that fundamentally redefines mesh-Gaussian integration. Whil
arXiv:2607.22673v1 Announce Type: cross Abstract: We present URHead, a unified representation for high-fidelity and animatable head avatars that fundamentally redefines mesh-Gaussian integration. While mesh-based methods offer precise geometric control but lack photorealistic detail, and Gaussian-based approaches achieve photorealism but suffer from poor structural consistency, existing hybrid solutions fail to fully leverage their complementary strengths. Our key contribution is a UV-space unification where both representations share a common UV parameterization. Through joint optimization with adaptive gaussian sampling, our method automatically learns to disentangle and allocate appropriate roles to each component. URHead maintains full parametric controllability while preserving subject-specific details, and outperforms existing state-of-the-art methods in reconstruction quality and animation consistency.
Related
- MeshLAM: Feed-Forward One-Shot Animatable Textured Mesh Avatar Reconstruction
- PiG-Avatar: Hierarchical Neural-Field-Guided Gaussian Avatars
- FFAvatar: Feed-Forward 4D Head Avatar Reconstruction from Sparse Portrait Images
- UIKA: Fast Universal Head Avatar from Pose-Free Images
Source: arXiv cs.CV | 2026-07-28