CHARM: Control-point-based 3D Anime Hairstyle Auto-Regressive Modeling

2025-09-25

AI Summary

Existing methods struggle to model highly stylized, segment-structured anime hairstyles due to reliance on dense meshes or hand-crafted splines, resulting in inefficient editing and poor compatibility with learning-based paradigms. This paper introduces the first control-point-based 3D sequential modeling framework for anime hairstyles: treating hairstyles as a learnable “hairstyle language,” we design a five-parameter control-point representation for individual hair strands and construct AnimeHair—a large-scale, segmented hairstyle dataset. We employ a Transformer architecture for autoregressive sequence generation, jointly modeling geometric details and topological structure. Our approach achieves state-of-the-art reconstruction accuracy and generation quality, enabling efficient editing, controllable synthesis, and diverse output.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Humans and AI: Game Design — Virtual Humans, NPCs and Autonomous Characters
• Natural Language Processing: Generation

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

We present CHARM, a novel parametric representation and generative framework for anime hairstyle modeling. While traditional hair modeling methods focus on realistic hair using strand-based or volumetric representations, anime hairstyle exhibits highly stylized, piecewise-structured geometry that challenges existing techniques. Existing works often rely on dense mesh modeling or hand-crafted spline curves, making them inefficient for editing and unsuitable for scalable learning. CHARM introduces a compact, invertible control-point-based parameterization, where a sequence of control points represents each hair card, and each point is encoded with only five geometric parameters. This efficient and accurate representation supports both artist-friendly design and learning-based generation. Built upon this representation, CHARM introduces an autoregressive generative framework that effectively generates anime hairstyles from input images or point clouds. By interpreting anime hairstyles as a sequential "hair language", our autoregressive transformer captures both local geometry and global hairstyle topology, resulting in high-fidelity anime hairstyle creation. To facilitate both training and evaluation of anime hairstyle generation, we construct AnimeHair, a large-scale dataset of 37K high-quality anime hairstyles with separated hair cards and processed mesh data. Extensive experiments demonstrate state-of-the-art performance of CHARM in both reconstruction accuracy and generation quality, offering an expressive and scalable solution for anime hairstyle modeling. Project page: https://hyzcluster.github.io/charm/

Problem

• Modeling highly stylized anime hairstyles with piecewise-structured geometry
• Overcoming inefficient dense mesh modeling and hand-crafted spline methods
• Creating scalable learning framework for anime hairstyle generation and editing

Innovation

• Control-point-based parametric representation for hair cards
• Autoregressive transformer framework interpreting hair language
• Large-scale AnimeHair dataset with separated hair cards