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

arXiv: https://arxiv.org/abs/2509.21114 · HTML: https://mlsanity.com/paper/2509.21114/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 64 references that are in the map.
- First posted on arXiv 25 Sep 2025.

## Builds on (most cited first, 29 of 29)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Dynamic Neural Radiance Fields for Monocular 4D Facial Avatar Reconstruction](https://mlsanity.com/paper/2012.03065/) (2020)
- [CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets](https://mlsanity.com/paper/2406.13897/) (2024)
- [MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers](https://mlsanity.com/paper/2311.15475/) (2023)
- [Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representation](https://mlsanity.com/paper/2306.17115/) (2023)
- [ATISS: Autoregressive Transformers for Indoor Scene Synthesis](https://mlsanity.com/paper/2110.03675/) (2021)
- [SceneFormer: Indoor Scene Generation with Transformers](https://mlsanity.com/paper/2012.09793/) (2020)
- [MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers](https://mlsanity.com/paper/2406.10163/) (2024)
- [H3DNet: 3D Object Detection Using Hybrid Geometric Primitives](https://mlsanity.com/paper/2006.05682/) (2020)
- [Fast and Flexible Indoor Scene Synthesis via Deep Convolutional Generative Models](https://mlsanity.com/paper/1811.12463/) (2018)
- [MeshAnything V2: Artist-Created Mesh Generation With Adjacent Mesh Tokenization](https://mlsanity.com/paper/2408.02555/) (2024)
- [LLaMA-Mesh: Unifying 3D Mesh Generation with Language Models](https://mlsanity.com/paper/2411.09595/) (2024)
- [Scaling Mesh Generation via Compressive Tokenization](https://mlsanity.com/paper/2411.07025/) (2024)
- [DeepMesh: Auto-Regressive Artist-mesh Creation with Reinforcement Learning](https://mlsanity.com/paper/2503.15265/) (2025)
- [GaussianHair: Hair Modeling and Rendering with Light-aware Gaussians](https://mlsanity.com/paper/2402.10483/) (2024)
- [Neural Haircut: Prior-Guided Strand-Based Hair Reconstruction](https://mlsanity.com/paper/2306.05872/) (2023)
- [HairStep: Transfer Synthetic to Real Using Strand and Depth Maps for Single-View 3D Hair Modeling](https://mlsanity.com/paper/2303.02700/) (2023)
- [Human Hair Reconstruction with Strand-Aligned 3D Gaussians](https://mlsanity.com/paper/2409.14778/) (2024)
- [GroomGen: A High-Quality Generative Hair Model Using Hierarchical Latent Representations](https://mlsanity.com/paper/2311.02062/) (2023)
- [Frankenstein: Generating Semantic-Compositional 3D Scenes in One Tri-Plane](https://mlsanity.com/paper/2403.16210/) (2024)
- [MonoHair: High-Fidelity Hair Modeling from a Monocular Video](https://mlsanity.com/paper/2403.18356/) (2024)
- [Perm: A Parametric Representation for Multi-Style 3D Hair Modeling](https://mlsanity.com/paper/2407.19451/) (2024)
- [DiffLocks: Generating 3D Hair from a Single Image using Diffusion Models](https://mlsanity.com/paper/2505.06166/) (2025)
- [GEM3D: GEnerative Medial Abstractions for 3D Shape Synthesis](https://mlsanity.com/paper/2402.16994/) (2024)
- [TANGLED: Generating 3D Hair Strands from Images with Arbitrary Styles and Viewpoints](https://mlsanity.com/paper/2502.06392/) (2025)
- [NOVA-3D: Non-overlapped Views for 3D Anime Character Reconstruction](https://mlsanity.com/paper/2405.12505/) (2024)

## Built on by (most cited first, 4 of 4)

- [HairGPT: Strand-as-Language Autoregressive Modeling for Realistic 3D Hairstyle Synthesis](https://mlsanity.com/paper/2605.08824/) (2026)
- [QuadLink: Autoregressive Quad-Dominant Mesh Generation via Point-Relation Learning](https://mlsanity.com/paper/2605.16813/) (2026)
- [HairCS: Reconstructing Strand-Based Hair from Hair Cards](https://mlsanity.com/paper/2609.16465/) (2026)
- [HairFlow: Modeling 3D Hair Strands with Multi-Modal Conditioned Diffusion](https://mlsanity.com/paper/2610.17348/) (2026)

## Abstract (arXiv)

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/