FHAvatar：从少量随手拍摄快速高保真重建面部与头发可组合的 3D 头像
FHAvatar: Fast and High-Fidelity Reconstruction of Face-and-Hair Composable 3D Head Avatar from Few Casual Captures
用平面高斯表示面部、发丝高斯表示头发，在纹理空间显式解耦，并借助聚合式 Transformer 骨干网络从多视角数据集中学习跨视角几何先验，使新身份仅需少量随手拍摄即可在数分钟内重建可实时驱动、可换发型的 3D 高斯头像。
原文依据 we explicitly decouple two components in texture space by representing the face with planar Gaussians and the hair with strand-based Gaussians
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论本文提出 FHAvatar，一种从任意数量视角重建具有可组合面部与头发组件的 3D 高斯头像的新框架。与以往在统一建模过程中耦合面部与头发表示的方法不同，我们在纹理空间中显式解耦这两个组件，用平面高斯表示面部、用基于发丝的高斯表示头发。为克服现有方法依赖密集多视角采集或昂贵的逐身份优化这一局限，我们提出一种聚合式 Transformer 骨干网络，从多视角数据集中学习几何感知的跨视角先验以及头部—头发的结构一致性，从而能够从少量随手拍摄中实现有效且高效的特征提取与融合。大量定量与定性实验表明，FHAvatar 仅凭新身份的少量观测即可在数分钟内达到最优的重建质量，同时支持实时动画、便捷的发型迁移与风格化编辑，拓宽了数字头像创建的易用性与适用范围。
英文原文摘要 1120 字符
We present FHAvatar, a novel framework for reconstructing 3D Gaussian avatars with composable face and hair components from an arbitrary number of views. Unlike previous approaches that couple facial and hair representations within a unified modeling process, we explicitly decouple two components in texture space by representing the face with planar Gaussians and the hair with strand-based Gaussians. To overcome the limitations of existing methods that rely on dense multi-view captures or costly per-identity optimization, we propose an aggregated transformer backbone to learn geometry-aware cross-view priors and head-hair structural coherence from multi-view datasets, enabling effective and efficient feature extraction and fusion from few casual captures. Extensive quantitative and qualitative experiments demonstrate that FHAvatar achieves state-of-the-art reconstruction quality from only a few observations of new identities within minutes, while supporting real-time animation, convenient hairstyle transfer, and stylized editing, broadening the accessibility and applicability of digital avatar creation.