Text-Conditioned Generative Model of 3D Strand-based Human Hairstyles

2024-01-01 · CVPR 2024 1 · Vanessa Sklyarova, Egor Zakharov, Otmar Hilliges, Michael J. Black, Justus Thies

We present HAAR a new strand-based generative model for 3D human hairstyles. Specifically based on textual inputs HAAR produces 3D hairstyles that could be used as production-level assets in modern computer graphics engines. Current AI-based generative models take advantage of powerful 2D priors to reconstruct 3D content in the form of point clouds meshes or volumetric functions. However by using the 2D priors they are intrinsically limited to only recovering the visual parts. Highly occluded hair structures can not be reconstructed with those methods and they only model the "outer shell" which is not ready to be used in physics-based rendering or simulation pipelines. In contrast we propose a first text-guided generative method that uses 3D hair strands as an underlying representation. Leveraging 2D visual question-answering (VQA) systems we automatically annotate synthetic hair models that are generated from a small set of artist-created hairstyles. This allows us to train a latent diffusion model that operates in a common hairstyle UV space. In qualitative and quantitative studies we demonstrate the capabilities of the proposed model and compare it to existing hairstyle generation approaches. For results please refer to our project page https://haar.is.tue.mpg.de/.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Question Answering Visual Question Answering Visual Question Answering (VQA)

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Latent Diffusion Model Diffusion models applied to latent spaces, which are normally built with (Variational) Autoencoders.

HAAR: Text-Conditioned Generative Model of 3D Strand-based Human Hairstyles

2023-12-18 · Vanessa Sklyarova, Egor Zakharov, Otmar Hilliges, Michael J. Black 외

We present HAAR, a new strand-based generative model for 3D human hairstyles. Specifically, based on textual inputs, HAAR produces 3D hairstyles that could be used as production-level assets in modern computer graphics e…

Question Answering Visual Question Answering Visual Question Answering (VQA)

DiffLocks: Generating 3D Hair from a Single Image using Diffusion Models

2025-05-09 · CVPR 2025 1 · Radu Alexandru Rosu, Keyu Wu, Yao Feng, Youyi Zheng 외

We address the task of generating 3D hair geometry from a single image, which is challenging due to the diversity of hairstyles and the lack of paired image-to-3D hair data. Previous methods are primarily trained on synt…

Image to 3D

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

2026-05-09 · Haimin Luo, Min Ouyang, Lan Xu, Jingyi Yu arxiv

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 diffusi…

TANGLED: Generating 3D Hair Strands from Images with Arbitrary Styles and Viewpoints

2025-02-10 · Pengyu Long, Zijun Zhao, Min Ouyang, Qingcheng Zhao 외

Hairstyles are intricate and culturally significant with various geometries, textures, and structures. Existing text or image-guided generation methods fail to handle the richness and complexity of diverse styles. We pre…

Diversity

Human Hair Reconstruction with Strand-Aligned 3D Gaussians

2024-09-23 · Egor Zakharov, Vanessa Sklyarova, Michael Black, Giljoo Nam 외

We introduce a new hair modeling method that uses a dual representation of classical hair strands and 3D Gaussians to produce accurate and realistic strand-based reconstructions from multi-view data. In contrast to recen…