One-shot Compositional 3D Head Avatars with Deformable Hair

2026-04-16

AI Summary

This work addresses the challenge of unrealistic hair dynamics in 3D head avatars generated from a single image, which often arises due to tight coupling between hair and facial geometry. The authors propose an explicit decoupling strategy that employs separate deformation mechanisms for hair and face using only a single frontal portrait. Facial details are preserved through FLAME-based mesh binding, while a cage-based structure enables physically plausible hair motion via Position-Based Dynamics. Unified rendering is achieved with 3D Gaussian Splatting, enhanced by semantic-label supervision and boundary-aware Gaussian redistribution to improve dynamic realism. Experiments demonstrate that the method simultaneously achieves high-fidelity facial geometry and natural hair dynamics under expressive deformations, gravity, and inertia, outperforming existing single-image approaches in perceptual quality.

Technology Category

• Computer Vision: 3D Computer Vision
• Humans and AI: Game Design — Virtual Humans, NPCs and Autonomous Characters
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

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.

Problem

• one-shot
• compositional 3D head avatars
• deformable hair
• hair dynamics
• 3D avatar

Innovation

• Compositional 3D Avatars
• Deformable Hair
• 3D Gaussian Splatting
• One-shot Reconstruction
• Position-Based Dynamics