A 3D Facial Reconstruction Evaluation Methodology: Comparing Smartphone Scans with Deep Learning Based Methods Using Geometry and Morphometry Criteria

TL;DR

This paper presents a comprehensive evaluation methodology for 3D facial reconstruction that combines geometric and morphometric criteria, enabling meaningful comparison of smartphone scans and deep learning methods against high-end ground truth models.

Contribution

It introduces a novel assessment framework that integrates morphometric analysis with traditional geometry-based benchmarks for 3D facial reconstruction evaluation.

Findings

Smartphone scans show promising shape preservation compared to high-end models.

Deep learning methods outperform traditional techniques in local shape accuracy.

The methodology provides a statistically robust way to validate low-cost 3D facial reconstruction.

Abstract

Three-dimensional (3D) facial shape analysis has gained interest due to its potential clinical applications. However, the high cost of advanced 3D facial acquisition systems limits their widespread use, driving the development of low-cost acquisition and reconstruction methods. This study introduces a novel evaluation methodology that goes beyond traditional geometry-based benchmarks by integrating morphometric shape analysis techniques, providing a statistical framework for assessing facial morphology preservation. As a case study, we compare smartphone-based 3D scans with state-of-the-art deep learning reconstruction methods from 2D images, using high-end stereophotogrammetry models as ground truth. This methodology enables a quantitative assessment of global and local shape differences, offering a biologically meaningful validation approach for low-cost 3D facial acquisition and reconstruction techniques.