HairGPT: Strand-as-Language Autoregressive Modeling for Realistic 3D Hairstyle Synthesis

TL;DR

HairGPT introduces a novel strand-centric autoregressive framework for realistic 3D hairstyle synthesis, enabling structured, controllable, and high-fidelity hair generation aligned with digital grooming workflows.

Contribution

It formulates hairstyle synthesis as a dual-decoupled sequence modeling problem, incorporating semantic and structural decoupling, geometric tokenization, and region-aware annotations for improved control and diversity.

Findings

Supports compositional editing and synthesis of complex hairstyles.

Achieves high-fidelity results across realistic and stylized domains.

Enables robust semantic conditioning for structured hair generation.

Abstract

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/