We propose a compositional method for constructing a complete 3D head avatar from a single image. Prior one-shot holistic approaches frequently fail to produce realistic hair dynamics during animation, largely due to inadequate decoupling of hair from the facial region, resulting in entangled geometry and unnatural deformations. Our method explicitly decouples hair from the face, modeling these components using distinct deformation paradigms while integrating them into a unified rendering pipeline. Furthermore, by leveraging image-to-3D lifting techniques, we preserve fine-grained textures from the input image to the greatest extent possible, effectively mitigating the common issue of high-frequency information loss in generalized models. Specifically, given a frontal portrait image, we first perform hair removal to obtain a bald image. Both the original image and the bald image are then lifted to dense, detail-rich 3D Gaussian Splatting (3DGS) representations. For the bald 3DGS, we rig it to a FLAME mesh via non-rigid registration with a prior model, enabling natural deformation that follows the mesh triangles during animation. For the hair component, we employ semantic label supervision combined with a boundary-aware reassignment strategy to extract a clean and isolated set of hair Gaussians. To control hair deformation, we introduce a cage structure that supports Position-Based Dynamics (PBD) simulation, allowing realistic and physically plausible transformations of the hair Gaussian primitives under head motion, gravity, and inertial effects. Striking qualitative results, including dynamic animations under diverse head motions, gravity effects, and expressions, showcase substantially more realistic hair behavior alongside faithfully preserved facial details, outperforming state-of-the-art one-shot methods in perceptual realism.
Given a single frontal image, we explicitly decouple hair and bald face components for separate reconstruction using 3DGS. The bald part is lifted to 3DGS and rigged to a parametric FLAME mesh via non-rigid registration for natural expression-driven deformation. The hair Gaussians are isolated and enclosed in a cage structure that supports Position-Based Dynamics (PBD) simulation for physically plausible motion under head pose, gravity, and inertia. Both components are seamlessly integrated into a unified rendering and animation pipeline, enabling coherent and realistic full-head driving.
@misc{sun2026oneshotcompositional3dhead,
title={One-shot Compositional 3D Head Avatars with Deformable Hair},
author={Yuan Sun and Xuan Wang and WeiLi Zhang and Wenxuan Zhang and Yu Guo and Fei Wang},
year={2026},
eprint={2604.14782},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2604.14782},
}