FlexAvatar: Flexible Large Reconstruction Model for Animatable Gaussian Head Avatars with Detailed Deformation
This provides a practical solution for animatable 3D avatar creation, which is incremental as it builds on existing reconstruction and deformation techniques.
The paper tackles the problem of creating high-fidelity 3D head avatars with detailed dynamic deformations from single or sparse images without requiring camera poses or expression labels, achieving superior 3D consistency and detailed dynamic realism compared to previous methods.
We present FlexAvatar, a flexible large reconstruction model for high-fidelity 3D head avatars with detailed dynamic deformation from single or sparse images, without requiring camera poses or expression labels. It leverages a transformer-based reconstruction model with structured head query tokens as canonical anchor to aggregate flexible input-number-agnostic, camera-pose-free and expression-free inputs into a robust canonical 3D representation. For detailed dynamic deformation, we introduce a lightweight UNet decoder conditioned on UV-space position maps, which can produce detailed expression-dependent deformations in real time. To better capture rare but critical expressions like wrinkles and bared teeth, we also adopt a data distribution adjustment strategy during training to balance the distribution of these expressions in the training set. Moreover, a lightweight 10-second refinement can further enhances identity-specific details in extreme identities without affecting deformation quality. Extensive experiments demonstrate that our FlexAvatar achieves superior 3D consistency, detailed dynamic realism compared with previous methods, providing a practical solution for animatable 3D avatar creation.