Skullptor: High Fidelity 3D Head Reconstruction in Seconds with Multi-View Normal Prediction

Noé Artru; Rukhshanda Hussain; Emeline Got; Alexandre Messier; David B. Lindell; Abdallah Dib

cs.CVFeb 24, 2026

Skullptor: High Fidelity 3D Head Reconstruction in Seconds with Multi-View Normal Prediction

Authors: Noé Artru, Rukhshanda Hussain, Emeline Got, Alexandre Messier, David B. Lindell, Abdallah Dib

Organizations: Ubisoft La Forge · University of Toronto · ÉTS Montréal · Vector Institute

Abstract

Reconstructing high-fidelity 3D head geometry from images is critical for a wide range of applications, yet existing methods face fundamental limitations. Traditional photogrammetry achieves exceptional detail but requires extensive camera arrays (25-200+ views), substantial computation, and manual cleanup in challenging areas like facial hair. Recent alternatives present a fundamental trade-off: foundation models enable efficient single-image reconstruction but lack fine geometric detail, while optimization-based methods achieve higher fidelity but require dense views and expensive computation. We bridge this gap with a hybrid approach that combines the strengths of both paradigms. Our method introduces a multi-view surface normal prediction model that extends monocular foundation models with cross-view attention to produce geometrically consistent normals in a feed-forward pass. We then leverage these predictions as strong geometric priors within an inverse rendering optimization framework to recover high-frequency surface details. Our approach outperforms state-of-the-art single-image and multi-view methods, achieving high-fidelity reconstruction on par with dense-view photogrammetry while reducing camera requirements and computational cost.

Figures & tables

Figure 2: Skullptor reconstructs 3D meshes in two stages. Multi-view normal prediction (Sec. 3.1) produces geometrically consistent surface normals from sparse input images by leveraging cross-view attention across all viewpoints. Mesh optimization (Sec. 3.2) then refines the 3D geometry using the predicted normals as geometric priors within an inverse rendering framework.

Dataset	Method	Avg. Angular Error $\downarrow$	Avg. Normal Grad. Err. $\downarrow$	$<$$$ (%)$ \uparrow$	$<$$$ (%)$ \uparrow$	$<$$$ (%)$ \uparrow$	Time (s) $\downarrow$
Multiface	Sapiens 0.3B	10.3	0.265	61.9	85.3	94.6	7.2
	Sapiens 2B	9.23	0.257	69.3	86.3	94.2	41.3
	DAViD	9.16	0.250	69.7	86.7	94.7	1.1
	Skullptor (Ours)	9.13	0.234	69.2	86.7	94.6	1.5
NPHM	Sapiens 0.3B	7.33	0.194	78.4	93.4	97.8	8.2
	Sapiens 2B	6.86	0.185	80.0	94.4	98.3	43.7

Table 1: Normal estimation comparison on Multiface and NPHM datasets.

Figure 3: Qualitative comparison of normal predictions on the NPHM dataset (rows 1–2) and Multiface dataset (rows 3–4).

Dataset	Method	Depth Error	Avg. Angular	Avg. Normal	$<$$$	$<$$$	$<$$$	Runtime	# Views
Dataset	Method	(mm) $\downarrow$	Error $\downarrow$	Gradient Error $\downarrow$	(%) $\uparrow$	(%) $\uparrow$	(%) $\uparrow$	(min) $\downarrow$
Multiface*	Meshroom (Photogrammetry)	0.467	5.43	0.143	85.1	95.8	99.0	7.8	26
	2D GS	5.73	10.7	0.206	68.6	85.4	92.5	50	26
	SuGaR	5.54	11.5	0.324	66.1	83.8	91.1	42	26
	Skullptor (Ours)	2.43	6.17	0.156	91.5	97.6	99.0	0.67	26
	Skullptor (Ours, 10 Views)	2.99	6.46	0.157	86.8	95.8	97.9	0.48	10

Table 2: Mesh reconstruction accuracy comparison on Multiface and NPHM datasets.

Figure 4: Qualitative comparison of mesh reconstruction methods on the NPHM (top) and Multiface (bottom) datasets.

Figure 5: Evolution of mesh reconstruction performance with the number of input camera views (NPHM dataset).

Figure 6: Visual comparison of the effect of the number of input views on reconstruction quality for Meshroom and Skullptor.

		Normal Metrics		Mesh Metrics
	Method	Ang. $\downarrow$	Grad. $\downarrow$	Depth $\downarrow$	Ang. $\downarrow$	Grad. $\downarrow$
NPHM	DAViD	7.80	0.188	2.68	5.68	0.115
	DAViD_ft_mono	8.43	0.174	3.53	6.04	0.116
	DAViD_ft_multi	7.13	0.176	2.87	5.98	0.113
	Skullptor	7.05	0.167	2.44	5.89	0.110
Multiface	DAViD	8.61	0.238	3.95	6.83	0.163

Table 3: Comparison of normal (left) and mesh (right) error.

Dataset	Normal Estimator	Depth (mm) $\downarrow$	Angular Err. $\downarrow$	Avg. Normal Grad. Err. $\downarrow$
Multiface	Sapiens 0.3B	5.28	8.75	0.177
	Sapiens 2B	3.79	6.76	0.167
	DAViD	3.74	6.73	0.163
	Skullptor (Ours)	3.20	6.45	0.157
NPHM	Sapiens 0.3B	6.38	8.23	0.124
	Sapiens 2B	6.76	7.91	0.121

Table S1 : Ablation study on normal estimator impact on final mesh quality (10 views).

Figure S1 : Qualitative impact of normal estimation quality on mesh reconstruction.

Figure S2 : Skullptor results on 12 phone-captured images.

	Male	Female
Number of subjects	18	32
Age range	18–64	18–75
Mean age	37.2	42.8
Age $<$ 25	9 (50%)	14 (44%)
Age 25–65	8 (44%)	12 (38%)
Age $>$ 65	1 (6%)	6 (19%)

Table S2 : Subject distribution in the Triplegangers training dataset.

Camera Sampling
Pitch angle $\theta_{\text{pitch}}$	$\mathcal{U}(-35^{\circ},35^{\circ})$
Yaw angle $\theta_{\text{yaw}}$	$\mathcal{U}(-90^{\circ},90^{\circ})$
Initial radius $\mathbf{r}$	2.0
Extra 3D translation $\mathbf{t}$	$\mathcal{U}(-0.2,0.2)^{3}$
Scale factor $z$	$\mathcal{U}(1.0,1.8)$
Projection Matrix

Table S3 : Camera Sampling and Projection Parameters

Figure S3 : Effect of initialization on mesh optimization. Vertex color indicates local edge length (Red short large edges, blue for small edges). Top: Sphere initialization. Bottom: Template mesh initialization. Facial characteristics from the template mesh are discarded, and both initializations converge to comparable results in 300 iterations.

3D Face Reconstruction

3D face reconstruction estimates facial shape and appearance from images or video to create usable models and avatars.

See all 54 papers

Any3DAvatar: Fast and High-Quality Full-Head 3D Avatar Reconstruction from Single Portrait Image
Apr 15, 2026Yujie Gao, Yao Xiao, Xiangnan Zhu +43D Avatar Generation 3D Reconstruction
Shanghai Jiao Tong University
Large-Scale High-Quality 3D Gaussian Head Reconstruction from Multi-View Captures
May 5, 2026Evangelos Ntavelis, Sean Wu, Mohamad Shahbazi +213D Gaussian Splatting Multi-View 3D Reconstruction
Apple
High-Fidelity Single-Image Head Modeling with Industry-Grade Topology
May 6, 2026Yunmu Wang, Zoubin Bi, Bowen Cai +63D Reconstruction Human Mesh Recovery
Alibaba Group, China

Apr 15, 2026J/K move · Enter open · S save

Any3DAvatar: Fast and High-Quality Full-Head 3D Avatar Reconstruction from Single Portrait Image

Yujie Gao, Yao Xiao, Xiangnan Zhu, Ya Li+3

Shanghai Jiao Tong University

3D Avatar Generation 3D Reconstruction Single-View 3D Reconstruction 3D Face Reconstruction Feed-Forward 3D Reconstruction 3D Gaussian Splatting

Open paper AskPDF arXiv

Reconstructing a complete 3D head from a single portrait remains challenging because existing methods still face a sharp quality-speed trade-off: high-fidelity pipelines often rely on multi-stage processing and per-subject optimization, while fast feed-forward models struggle with complete geometry and fine appearance details. To bridge this gap, we propose Any3DAvatar, a fast and high-quality method for single-image 3D Gaussian head avatar generation, whose fastest setting reconstructs a full head in under one second while preserving high-fidelity geometry and texture. First, we build AnyHead, a unified data suite that combines identity diversity, dense multi-view supervision, and realistic accessories, filling the main gaps of existing head data in coverage, full-head geometry, and complex appearance. Second, rather than sampling unstructured noise, we initialize from a Plücker-aware structured 3D Gaussian scaffold and perform one-step conditional denoising, formulating full-head reconstruction into a single forward pass while retaining high fidelity. Third, we introduce auxiliary view-conditioned appearance supervision on the same latent tokens alongside 3D Gaussian reconstruction, improving novel-view texture details at zero extra inference cost. Experiments show that Any3DAvatar outperforms prior single-image full-head reconstruction methods in rendering fidelity while remaining substantially faster.

Abstract

3D Face Reconstruction

Explore similar work

Any3DAvatar: Fast and High-Quality Full-Head 3D Avatar Reconstruction from Single Portrait Image

Large-Scale High-Quality 3D Gaussian Head Reconstruction from Multi-View Captures

High-Fidelity Single-Image Head Modeling with Industry-Grade Topology