Large Scale 3D Morphable Models

James Booth,Allan Ponniah,Anastasios Roussos,David Dunaway,Stefanos Zafeiriou

doi:10.1007/s11263-017-1009-7

Abstract

We present large scale facial model (LSFM)—a 3D Morphable Model (3DMM) automatically constructed from 9663 distinct facial identities. To the best of our knowledge LSFM is the largest-scale Morphable Model ever constructed, containing statistical information from a huge variety of the human population. To build such a large model we introduce a novel fully automated and robust Morphable Model construction pipeline, informed by an evaluation of state-of-the-art dense correspondence techniques. The dataset that LSFM is trained on includes rich demographic information about each subject, allowing for the construction of not only a global 3DMM model but also models tailored for specific age, gender or ethnicity groups. We utilize the proposed model to perform age classification from 3D shape alone and to reconstruct noisy out-of-sample data in the low-dimensional model space. Furthermore, we perform a systematic analysis of the constructed 3DMM models that showcases their quality and descriptive power. The presented extensive qualitative and quantitative evaluations reveal that the proposed 3DMM achieves state-of-the-art results, outperforming existing models by a large margin. Finally, for the benefit of the research community, we make publicly available the source code of the proposed automatic 3DMM construction pipeline, as well as the constructed global 3DMM and a variety of bespoke models tailored by age, gender and ethnicity.

Highlights

A 3D Morphable Model (3DMM) is constructed by performing some form of dimensionality reduction, typically principal component analysis (PCA), on a training set of facial meshes
To provide greater insight into how demographic variability and training set size impact the performance of 3D Morphable Models, we explore in detail the impact of these two factors on the intrinsics and fitting application of our model (Figs. 16, 17)
By making both the large scale facial model (LSFM) software pipeline and models available, we help to usher in an exciting new era of large scale 3DMMs, where construction is radically simpler and large-scale models can become commonplace

Summary

Introduction

A 3DMM is constructed by performing some form of dimensionality reduction, typically principal component analysis (PCA), on a training set of facial meshes. This is feasible if and only if each mesh is first re-parametrised into a consistent form where the number of vertices, the triangu-. The usages of these models have expanded massively into new fields over the last 15 years With emerging applications such as virtual reality (VR), autonomous vehicles, and depth-camera equipped consumer robotics, it is not hard to image a future where 3D applications of 3DMMs are more obvious and widespread than the initial application to 2D images.

Objectives

Methods

Findings

Conclusion