English

HairOrbit: Multi-view Aware 3D Hair Modeling from Single Portraits

Computer Vision and Pattern Recognition 2026-04-06 v1

Abstract

Reconstructing strand-level 3D hair from a single-view image is highly challenging, especially when preserving consistent and realistic attributes in unseen regions. Existing methods rely on limited frontal-view cues and small-scale/style-restricted synthetic data, often failing to produce satisfactory results in invisible regions. In this work, we propose a novel framework that leverages the strong 3D priors of video generation models to transform single-view hair reconstruction into a calibrated multi-view reconstruction task. To balance reconstruction quality and efficiency for the reformulated multi-view task, we further introduce a neural orientation extractor trained on sparse real-image annotations for better full-view orientation estimation. In addition, we design a two-stage strand-growing algorithm based on a hybrid implicit field to synthesize the 3D strand curves with fine-grained details at a relatively fast speed. Extensive experiments demonstrate that our method achieves state-of-the-art performance on single-view 3D hair strand reconstruction on a diverse range of hair portraits in both visible and invisible regions.

Cite

@article{arxiv.2604.02867,
  title  = {HairOrbit: Multi-view Aware 3D Hair Modeling from Single Portraits},
  author = {Leyang Jin and Yujian Zheng and Bingkui Tong and Yuda Qiu and Zhenyu Xie and Hao Li},
  journal= {arXiv preprint arXiv:2604.02867},
  year   = {2026}
}

Comments

17 pages, 6 figures