HairOrbit: Multi-view Aware 3D Hair Modeling from Single Portraits
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911564684066816 |
|---|---|
| author | Jin, Leyang Zheng, Yujian Tong, Bingkui Qiu, Yuda Xie, Zhenyu Li, Hao |
| author_facet | Jin, Leyang Zheng, Yujian Tong, Bingkui Qiu, Yuda Xie, Zhenyu Li, Hao |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_02867 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | HairOrbit: Multi-view Aware 3D Hair Modeling from Single Portraits Jin, Leyang Zheng, Yujian Tong, Bingkui Qiu, Yuda Xie, Zhenyu Li, Hao Computer Vision and Pattern Recognition 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. |
| title | HairOrbit: Multi-view Aware 3D Hair Modeling from Single Portraits |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.02867 |