SCALP: Semi-Supervised Statistical Shape Modeling from Imperfect 3D Photogrammetry via Landmark-Anchored Spectral Warp

2026-07-31

AI Summary

This study addresses the challenge of constructing reliable statistical shape models from clinical infant craniofacial 3D scans, which are often noisy, incomplete, and lack point-wise correspondences. To overcome this, the authors propose a two-stage approach: first, a semi-supervised Point Transformer accurately localizes craniofacial landmarks with minimal manual annotation; second, these landmarks serve as anchors to guide Laplace–Beltrami spectral deformation, enabling the generation of dense correspondences and automatic segmentation of the cranial region directly from raw scans. This work presents the first integration of semi-supervised learning with spectral deformation, achieving high-quality statistical shape models from imperfect clinical data without extensive preprocessing. Experiments demonstrate significant improvements over existing unsupervised methods on infant photogrammetric datasets, offering a clinically viable, radiation-free pathway for cranial shape analysis.

Abstract

Correspondence-based statistical shape modeling (SSM) is vital for population-level morphometric analysis, but conventional pipelines assume clean, fully registered surfaces. Real-world clinical photogrammetry scans are often noisy, partial, and cluttered, hindering the adoption of radiation-free surface imaging as a safe alternative to computed tomography (CT) for infant craniosynostosis. We present SCALP (Semi-supervised Correspondence via lAndmark Localization and sPectral warping), a two-stage framework that constructs consistent shape models directly from raw, imperfect surface scans. First, a semi-supervised Point Transformer leverages a small expert-annotated dataset alongside a large unlabeled cohort to accurately localize craniofacial landmarks with minimal annotation overhead. Second, these landmarks anchor a Laplace--Beltrami spectral deformation of an anatomical template, generating dense correspondences while naturally isolating the cranium from peripheral scanning clutter without manual preprocessing. Experiments on infant photogrammetry scans demonstrate that SCALP consistently outperforms state-of-the-art unsupervised point-cloud approaches, offering a clinically practical pathway toward objective, radiation-free head shape analysis.

Problem

• statistical shape modeling
• 3D photogrammetry
• craniosynostosis
• correspondence
• semi-supervised learning

Innovation

• Semi-supervised learning
• Statistical shape modeling
• Spectral correspondence
• 3D photogrammetry
• Landmark localization