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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: He, Yuze, Zhou, Yanning, Zhao, Wang, Ye, Jingwen, Bai, Yushi, Xiao, Kaiwen, Liu, Yong-Jin, Sun, Zhongqian, Yang, Wei
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916970199252992
author He, Yuze
Zhou, Yanning
Zhao, Wang
Ye, Jingwen
Bai, Yushi
Xiao, Kaiwen
Liu, Yong-Jin
Sun, Zhongqian
Yang, Wei
author_facet He, Yuze
Zhou, Yanning
Zhao, Wang
Ye, Jingwen
Bai, Yushi
Xiao, Kaiwen
Liu, Yong-Jin
Sun, Zhongqian
Yang, Wei
contents 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/
format Preprint
id arxiv_https___arxiv_org_abs_2509_21114
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CHARM: Control-point-based 3D Anime Hairstyle Auto-Regressive Modeling
He, Yuze
Zhou, Yanning
Zhao, Wang
Ye, Jingwen
Bai, Yushi
Xiao, Kaiwen
Liu, Yong-Jin
Sun, Zhongqian
Yang, Wei
Graphics
Computer Vision and Pattern Recognition
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/
title CHARM: Control-point-based 3D Anime Hairstyle Auto-Regressive Modeling
topic Graphics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.21114