# HairFlow: Modeling 3D Hair Strands with Multi-Modal Conditioned Diffusion

arXiv: https://arxiv.org/abs/2610.17348 · HTML: https://mlsanity.com/paper/2610.17348/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 43 references that are in the map.
- First posted on arXiv 12 Oct 2026.

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

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [3DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models](https://mlsanity.com/paper/2301.11445/) (2023)
- [Dora: Sampling and Benchmarking for 3D Shape Variational Auto-Encoders](https://mlsanity.com/paper/2412.17808/) (2024)
- [HairCLIP: Design Your Hair by Text and Reference Image](https://mlsanity.com/paper/2112.05142/) (2021)
- [Neural Strands: Learning Hair Geometry and Appearance from Multi-View Images](https://mlsanity.com/paper/2207.14067/) (2022)
- [MeGA: Hybrid Mesh-Gaussian Head Avatar for High-Fidelity Rendering and Head Editing](https://mlsanity.com/paper/2404.19026/) (2024)
- [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)
- [NeuralHDHair: Automatic High-fidelity Hair Modeling from a Single Image Using Implicit Neural Representations](https://mlsanity.com/paper/2205.04175/) (2022)
- [HAAR: Text-Conditioned Generative Model of 3D Strand-based Human Hairstyles](https://mlsanity.com/paper/2312.11666/) (2023)
- [GroomGen: A High-Quality Generative Hair Model Using Hierarchical Latent Representations](https://mlsanity.com/paper/2311.02062/) (2023)
- [DeepSketchHair: Deep Sketch-based 3D Hair Modeling](https://mlsanity.com/paper/1908.07198/) (2019)
- [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)
- [3D Gaussian Head Avatars with Expressive Dynamic Appearances by Compact Tensorial Representations](https://mlsanity.com/paper/2504.14967/) (2025)
- [Towards Unified 3D Hair Reconstruction from Single-View Portraits](https://mlsanity.com/paper/2409.16863/) (2024)
- [Im2Haircut: Single-view Strand-based Hair Reconstruction for Human Avatars](https://mlsanity.com/paper/2509.01469/) (2025)
- [TANGLED: Generating 3D Hair Strands from Images with Arbitrary Styles and Viewpoints](https://mlsanity.com/paper/2502.06392/) (2025)
- [Auto Hair Card Extraction for Smooth Hair with Differentiable Rendering](https://mlsanity.com/paper/2505.18805/) (2025)
- [StrandHead: Text to Hair-Disentangled 3D Head Avatars Using Human-Centric Priors](https://mlsanity.com/paper/2412.11586/) (2024)
- [CHARM: Control-point-based 3D Anime Hairstyle Auto-Regressive Modeling](https://mlsanity.com/paper/2509.21114/) (2025)
- [StrandDesigner: Towards Practical Strand Generation with Sketch Guidance](https://mlsanity.com/paper/2508.01650/) (2025)
- [DGH: Dynamic Gaussian Hair](https://mlsanity.com/paper/2512.17094/) (2025)
- [HairOrbit: Multi-view Aware 3D Hair Modeling from Single Portraits](https://mlsanity.com/paper/2604.02867/) (2026)
- [HairGPT: Strand-as-Language Autoregressive Modeling for Realistic 3D Hairstyle Synthesis](https://mlsanity.com/paper/2605.08824/) (2026)
- [HairLRM: Strand-based Hair Modeling via Large Reconstruction Models](https://mlsanity.com/paper/2606.15238/) (2026)
- [Strand-based Hairstyle Generation via Large Reconstruction and Multimodal Models](https://mlsanity.com/paper/2608.13679/) (2026)
- [HairCS: Reconstructing Strand-Based Hair from Hair Cards](https://mlsanity.com/paper/2609.16465/) (2026)

## Abstract (arXiv)

Modeling 3D hair strands is challenging due to complex hairstyle geometry, scarce high-quality training data, and incomplete or noisy input observations. Foundation models offer broader hairstyle priors, but their outputs are not directly usable for strand-based rendering and simulation. Existing approaches require costly per-instance optimization to fit hair priors to meshes from foundation models and 2D orientations from specialized predictors trained on limited hair data, restricting efficiency and generalization. We present HairFlow, a multimodal conditioned diffusion framework for efficient and controllable hair strands modeling. HairFlow conditions strand generation on two complementary representations: a coarse mesh that constrains global shape and multi-view sketches that specify local strand flow. HairFlow combines an Orientation VAE with a conditioned diffusion transformer to generate volumetric fields that are traced into explicit strands. To overcome the lack of paired sketch-strand training data, we introduce an automatic synthesis pipeline that generates geometrically aligned multi-view sketches with diverse styles representative of inference-time inputs. Experiments show that HairFlow generates plausible 3D strands that faithfully follow the input conditions across diverse hairstyles, substantially reduces inference time, and supports flexible multimodal control.