StrandHead：使用头发几何先验将文本转换为分离的三维头部化身

StrandHead: Text to Strand-Disentangled 3D Head Avatars Using Hair Geometric Priors

December 16, 2024

作者: Xiaokun Sun, Zeyu Cai, Zhenyu Zhang, Ying Tai, Jian Yang

cs.AI

摘要

虽然发型反映了独特的个性，但现有的头像生成方法未能对实际发型进行建模，因为其通常采用的是一般或纠缠的表示方法。我们提出了StrandHead，一种新颖的文本到3D头像生成方法，能够生成具有串表示的脱缰3D头发。在不使用3D数据进行监督的情况下，我们展示了可以通过提炼2D生成扩散模型从提示中生成逼真的头发串。为此，我们提出了一系列可靠的先验，涉及形状初始化、几何基元和统计发型特征，从而实现稳定的优化和与文本对齐的性能。大量实验证明，StrandHead实现了生成的3D头像和头发的最先进的真实性和多样性。生成的3D头发还可以轻松地在虚幻引擎中进行物理模拟和其他应用。代码将在以下网址提供：https://xiaokunsun.github.io/StrandHead.github.io。

English

While haircut indicates distinct personality, existing avatar generation methods fail to model practical hair due to the general or entangled representation. We propose StrandHead, a novel text to 3D head avatar generation method capable of generating disentangled 3D hair with strand representation. Without using 3D data for supervision, we demonstrate that realistic hair strands can be generated from prompts by distilling 2D generative diffusion models. To this end, we propose a series of reliable priors on shape initialization, geometric primitives, and statistical haircut features, leading to a stable optimization and text-aligned performance. Extensive experiments show that StrandHead achieves the state-of-the-art reality and diversity of generated 3D head and hair. The generated 3D hair can also be easily implemented in the Unreal Engine for physical simulation and other applications. The code will be available at https://xiaokunsun.github.io/StrandHead.github.io.