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

Leyang Jin; Yujian Zheng; Bingkui Tong; Yuda Qiu; Zhenyu Xie; Hao Li

cs.CVApr 3, 2026

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

Authors: Leyang Jin, Yujian Zheng, Bingkui Tong, Yuda Qiu, Zhenyu Xie, Hao Li

Organizations: Mohamed bin Zayed University of Artificial Intelligence · SSE, The Chinese University of Hong Kong, Shenzhen · Pinscreen

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.

Figures & tables

Figure 1: We propose a novel framework for strand-level single-view 3D hair reconstruction. Given a frontal-view portrait (a), we first synthesize corresponding calibrated multi-view images (b) on a camera orbit, then reconstruct multi-view aware 3D hair strands (c). Note that the left view in (c) is rendered with about 10k strands to better visualize the geometry, while the other 3 views are rendered with 100k.

Figure 2: Overview of HairOrbit . Given a single portrait, HairOrbit converts single-view 3D hair reconstruction into a multi-view task.

	nastya	ksyusha	jenya	shortCurly	whiteCurly	midWavy	midCurly	Overall
#Views	62	66	70	58	42	33	64	395
Gabor	11.88	16.56	18.88	18.87	24.56	11.31	10.79	16.05
HairStep	6.28	10.98	13.16	13.68	21.57	6.32	5.54	10.88
Ours	1.79	4.97	6.09	6.72	13.50	2.15	2.12	5.13

Table 1: Quantitative comparisons of full-view orientation extraction (mean angle error, lower is better). #Views means the number of annotated views.

Figure 3: Qualitative comparisons of full-view orientation extraction. Results of HairStep have been converted to orientation maps.

Figure 4: Comparisons on multi-view generation.

Figure 5: Qualitative comparison on single-view 3D strands reconstruction. For every example, we show (a) the input image and the reconstructed 3D hair strands rendered in multiple views of (b) Ours, (c) Im2Haircut, (d) HairStep and (e) Difflocks.

Metric	HairStep	DiffLocks	Im2Haircut	Ours
HairSale ( ∘ ) $\downarrow$	17.38	26.50	16.24	12.83
HairRida ( $\%$ ) $\uparrow$	77.01	69.67	79.38	80.52
IoU $\uparrow$	0.639	0.593	0.757	0.847

Table 2: Quantitative comparisons on single-view 3D strands reconstruction with HairSale and IoU.

Figure 6: Qualitative comparisons of ablation study.

Method	@Input View		@Synthesized 8 Views
Method	HairSale ( ∘ ) ↓	IoU ↑	HairSale ( ∘ ) ↓	IoU ↑
$\bm{C_{0}}$	16.42 (-27.98%)	0.794	13.45 (-34.90%)	0.878
$\bm{C_{1}}$	13.70 (-6.78%)	0.828	10.37 (-4.01%)	0.887
$\bm{C_{2}}$	19.10 (-48.87%)	0.680	24.14 (-142.1%)	0.658
Full	12.83	0.847	9.97	0.900

Table 3: Quantitative comparisons of ablation study. Blue values denote the performance degradation (%) compared to Full .

3D Reconstruction

3D reconstruction recovers a scene’s shape, appearance, and camera motion from images, video, depth, or other sensor measurements.

See all 955 papers

EfficientMonoHair: Fast Strand-Level Reconstruction from Monocular Video via Multi-View Direction Fusion
Apr 7, 2026Da Li, Dominik Engel, Deng Luo +13D Reconstruction Monocular 3D Reconstruction
King Abdullah University of Science and Technology, Saudi Arabia
HairLRM: Strand-based Hair Modeling via Large Reconstruction Models
Jun 13, 2026Yuefan Shen, Yican Dong, Xiufeng Huang +33D Reconstruction Generative Modeling
LIGHTSPEED, China · State Key Lab of CAD and CG, Zhejiang University, China · Hong Kong Baptist University, China +1
HairFlow: Modeling 3D Hair Strands with Multi-Modal Conditioned Diffusion
Oct 12, 2026Yating Wang, Kui Wu, Ran Yi +5Conditional Diffusion Models 3D Diffusion Models
Shanghai Jiao Tong University · LIGHTSPEED

Apr 7, 2026J/K move · Enter open · S save

EfficientMonoHair: Fast Strand-Level Reconstruction from Monocular Video via Multi-View Direction Fusion

Da Li, Dominik Engel, Deng Luo, Ivan Viola

King Abdullah University of Science and Technology, Saudi Arabia

3D Reconstruction Monocular 3D Reconstruction

Open paper AskPDF arXiv

Strand-level hair geometry reconstruction is a fundamental problem in virtual human modeling and the digitization of hairstyles. However, existing methods still suffer from a significant trade-off between accuracy and efficiency. Implicit neural representations can capture the global hair shape but often fail to preserve fine-grained strand details, while explicit optimization-based approaches achieve high-fidelity reconstructions at the cost of heavy computation and poor scalability. To address this issue, we propose EfficientMonoHair, a fast and accurate framework that combines the implicit neural network with multi-view geometric fusion for strand-level reconstruction from monocular video. Our method introduces a fusion-patch-based multi-view optimization that reduces the number of optimization iterations for point cloud direction, as well as a novel parallel hair-growing strategy that relaxes voxel occupancy constraints, allowing large-scale strand tracing to remain stable and robust even under inaccurate or noisy orientation fields. Extensive experiments on representative real-world hairstyles demonstrate that our method can robustly reconstruct high-fidelity strand geometries with accuracy. On synthetic benchmarks, our method achieves reconstruction quality comparable to state-of-the-art methods, while improving runtime efficiency by nearly an order of magnitude.

Abstract

3D Reconstruction

Explore similar work

EfficientMonoHair: Fast Strand-Level Reconstruction from Monocular Video via Multi-View Direction Fusion

HairLRM: Strand-based Hair Modeling via Large Reconstruction Models

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