Expression invariant 3D face recognition with a Morphable Model

By Brian Amberg, Reinhard Knothe, Thomas Vetter. 2008

213 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Generating 3D faces using Convolutional Mesh Autoencoders (2018, methodology): “[1] combine a neutral shape PCA model with a PCA model on the expression residuals from the neutral shape.”
paGAN (2018, unknown): “In order to model the variation in expressions, previous work [Amberg et al. 2008] combine a PCA model of a neutral-expression face shape with a PCA space derived from the residual vectors of different expressions to the neutral pose.”
A 3D Morphable Model Learnt from 10,000 Faces (2016, methodology): “[3] extended this approach to emotive facial shapes by adopting an additional PCA modeling of the offsets from the neutral pose.”
Multilinear Wavelets: A Statistical Shape Space for Human Faces (2014, methodology): “[1] extend the morphable model to consider expressions, by combining it with a PCA model for expression offsets with respect to the neutral expression geometry.”
Nonlinear 3D Face Morphable Model (2018, methodology): “3DMM has been widely applied in numerous areas, such as computer vision [4, 43], graphics [1], human behavioral analysis [2] and craniofacial surgery [34].”
Robust semantic analysis by synthesis of 3D facial motion (2011, background): “Their strength has been recently shown in the context of expression invariant face recognition with a model consisting of identities and natural expression keyframes recorded from a large corpus of subjects [1].”
Large Scale 3D Morphable Models (2017, methodology): “3DMMs have since been widely applied in numerous areas in computer vision, human behavioral analysis, computer graphics, craniofacial surgery and large-scale facial pheno-typing (Blanz and Vetter 2003, Amberg et al. 2008, Aldrian and Smith 2013, Staal et al. 2015, Hammond and Suttie 2012) (Fig.”
Morphable Face Models - An Open Framework (2017, methodology): “2) Expression Model: We extend the original face model to a multi-linear model to handle expressions as described in [23].”
Multilinear Autoencoder for 3D Face Model Learning (2018, background): “Generative modeling of 3D faces Linear models have first been introduced to model face shape in neutral expression along with appearance information [3] and later been extended to include expression change as a linear factor [1].”
A 3D Face Model for Pose and Illumination Invariant Face Recognition (2009, methodology): “A similar method has also been applied to stereo data [3] and 3D scans [2].”
Expressive Body Capture: 3D Hands, Face, and Body From a Single Image (2019, background): “There is also an extensive literature on modelling hands [39, 53, 57, 58, 68, 69, 71, 74, 75] and faces [4, 9, 11, 13, 14, 43, 63, 76, 79] in 3D but in isolation from the rest of the body.”
Review of statistical shape spaces for 3D data with comparative analysis for human faces (2012, methodology): “Amberg et al. [11] extended the morphable model to model expression variation by computing offsets from the neutral pose and performing PCA over these offset surfaces.”