用分丝作为语言构建3D发型，实现可控且逼真的生成。
HairGPT: Strand-as-Language Autoregressive Modeling for Realistic 3D Hairstyle Synthesis
- 将发丝视为生成基本单元，分步建模发型结构与风格。
- 支持稀有复杂发型生成，且在真实与艺术风格中均保持高保真。
- 适合影视动画、虚拟形象设计等需要精细控制的场景。
头发是视觉与文化表达的重要载体，但其数字建模因流动与结构的双重特性而困难重重。现有生成方法多依赖连续扩散场，混淆了全局拓扑与局部纹理，遮蔽了发型的语义与结构组织。为此，我们提出 HairGPT，一种以发丝为中心的框架，将真实3D发型合成建模为双解耦的自回归序列问题。方法在语义头皮区域间实现空间解耦，在分层发丝表示上实现结构解耦，从整体布局逐步推进至细节风格。引入几何分词器与区域感知语义标注，引导发丝级生成，支持组合编辑、罕见复杂发型合成及风格化领域适配。通过契合数字造型流程，HairGPT 将发型生成从模糊纹理合成转变为结构化、语义可控的创作过程，支持强语义条件输入，在真实与风格化领域均实现高保真结果。
原文摘要 · Abstract (English)
Hair is a rich medium of visual and cultural expression, yet its digital modeling remains challenging due to the duality of fluidity and structure. Many existing generative approaches rely primarily on continuous diffusion fields, which entangle global topology with local texture and obscure the semantic and structural organization of hairstyles. To address this, we propose HairGPT, a strand-centric framework that treats strands as generative primitives and formulates realistic 3D hairstyle synthesis as a dual-decoupled autoregressive sequence modeling problem. Our method applies spatial decoupling across semantic scalp regions and structural decoupling along a hierarchical strand representation, progressing from global layout to fine-grained style. We further introduce a geometric tokenizer and region-aware semantic annotations to guide strand-level generation, enabling compositional editing, synthesis of rare and complex hairstyles, and adaptation to stylized domains. By aligning generative modeling with the workflow of digital grooming, HairGPT turns hair generation from opaque texture synthesis into a structured and semantically controllable authoring process, supporting robust semantic conditioning and high-fidelity results across realistic and stylized domains. Project Page: https://haiminluo.github.io/hairgpt/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。