Robust Registration and Geometry Estimation from Unstructured Facial Scans

TL;DR

This paper introduces a novel iterative pipeline for aligning unstructured 3D facial scans and registering them to a shape variation model, improving accuracy and correcting mislabeled data.

Contribution

It presents a new interwoven pose estimation and mesh warping method that enhances alignment accuracy and handles unstructured, incomplete facial scan data.

Findings

Average point-to-surface distance of 0.5mm achieved

Successfully aligned full profile scans and corrected mislabeled data

Demonstrated effectiveness on the NDOff-2007 dataset with 7,358 scans

Abstract

Commercial off the shelf (COTS) 3D scanners are capable of generating point clouds covering visible portions of a face with sub-millimeter accuracy at close range, but lack the coverage and specialized anatomic registration provided by more expensive 3D facial scanners. We demonstrate an effective pipeline for joint alignment of multiple unstructured 3D point clouds and registration to a parameterized 3D model which represents shape variation of the human head. Most algorithms separate the problems of pose estimation and mesh warping, however we propose a new iterative method where these steps are interwoven. Error decreases with each iteration, showing the proposed approach is effective in improving geometry and alignment. The approach described is used to align the NDOff-2007 dataset, which contains 7,358 individual scans at various poses of 396 subjects. The dataset has a number of full profile scans which are correctly aligned and contribute directly to the associated mesh geometry. The dataset in its raw form contains a significant number of mislabeled scans, which are identified and corrected based on alignment error using the proposed algorithm. The average point to surface distance between the aligned scans and the produced geometries is one half millimeter.