Morphable Face Models - An Open Framework

TL;DR

This paper introduces an open-source framework for face registration using Gaussian process models, enabling detailed 3D face analysis and expression modeling, with applications demonstrated on multiple datasets.

Contribution

It presents a novel face registration strategy considering symmetry and multi-scale details, and releases an open-source pipeline for model building and analysis.

Findings

Open-source registration framework demonstrated on BU3D-FE database.

Enhanced Basel Face Model with better age distribution and expressions.

Application of analysis-by-synthesis for 2D face image adaptation.

Abstract

In this paper, we present a novel open-source pipeline for face registration based on Gaussian processes as well as an application to face image analysis. Non-rigid registration of faces is significant for many applications in computer vision, such as the construction of 3D Morphable face models (3DMMs). Gaussian Process Morphable Models (GPMMs) unify a variety of non-rigid deformation models with B-splines and PCA models as examples. GPMM separate problem specific requirements from the registration algorithm by incorporating domain-specific adaptions as a prior model. The novelties of this paper are the following: (i) We present a strategy and modeling technique for face registration that considers symmetry, multi-scale and spatially-varying details. The registration is applied to neutral faces and facial expressions. (ii) We release an open-source software framework for registration and model-building, demonstrated on the publicly available BU3D-FE database. The released pipeline also contains an implementation of an Analysis-by-Synthesis model adaption of 2D face images, tested on the Multi-PIE and LFW database. This enables the community to reproduce, evaluate and compare the individual steps of registration to model-building and 3D/2D model fitting. (iii) Along with the framework release, we publish a new version of the Basel Face Model (BFM-2017) with an improved age distribution and an additional facial expression model.