A 3D Morphable Model Learnt from 10,000 Faces

Abstract

We present Large Scale Facial Model (LSFM) -a 3D Morphable Model (3DMM) automatically constructed from 9,663 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. The dataset that LSFM is trained on includes rich demographic information about each subject, allowing for the construction of not only a global 3DMM but also models tailored for specific age, gender or ethnicity groups. As an application example, we utilise the proposed model to perform age classification from 3D shape alone. Furthermore, we perform a systematic analysis of the constructed 3DMMs 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. In addition, the constructed global 3DMM and a variety of bespoke models tailored by age, gender and ethnicity are available on application to researchers involved in medically oriented research.

rtCaptcha: A Real-Time CAPTCHA Based Liveness Detection System

“…Once built, a 3DMM is ready for reconstruction according to facial attributes of a victim's face. The details of building a 3D face model could be found in [27], but the overall pipeline is as follows. First, facial landmarks which express pose, shape and expression are extracted from the victim's face.…”

“…3DMMs are the statistical 3D representations built on facial textures and shapes of many different subjects (e.g. 10,000 faces in [27]) by incorporating with their facial expressions and physical attributes at the same time. Once built, a 3DMM is ready for reconstruction according to facial attributes of a victim's face.…”

[Invited Paper] Recent Advances in Biometric Recognition

“…f.cootes/software/am_tools_doc/index.html puter technology. Large Scale Facial Model (LSFM) has been created from a large scale dataset by Booth et al 10) , where the dataset includes face images and 3D data captured from 9,663 subjects. LSFM is a parametric 3D facial model of head pose, facial expression, age and ethnicity.…”

Face Normals "In-the-Wild" Using Fully Convolutional Networks

“…Furthermore, there exists a large amount of publicly available imagery of faces and human faces are of significant interest to a number of fields including entertainment, medicine, and psychology. The two main lines of research consist of (a) Shape from Shading (SfS) methods which can also potentially employ a statistical face prior [71,3,65,12,56,59,57], or (b) building and fitting a 3D Morphable Model (3DMM) [8,7,1]. A convnet normals face shape Figure 1: Depiction of our pipeline for 3D face shape estimation.…”