Multilinear Wavelets: A Statistical Shape Space for Human Faces

By Alan Brunton, Timo Bolkart, Stefanie Wuhrer. 2014

101 citations recorded by the source corpus.

We present a statistical model for 3D human faces in varying expression, which decomposes the surface of the face using a wavelet transform, and learns many localized, decorrelated multilinear models on the resulting coefficients. Using this model we are able to reconstruct faces from noisy and occluded 3D face scans, and facial motion sequences. Accurate reconstruction of face shape is important for applications such as tele-presence and gaming. The localized and multi-scale nature of our model allows for recovery of fine-scale detail while retaining robustness to severe noise and occlusion, and is computationally efficient and scalable. We validate these properties experimentally on challenging data in the form of static scans and motion sequences. We show that in comparison to a global multilinear model, our model better preserves fine detail and is computationally faster, while in comparison to a localized PCA model, our model better handles variation in expression, is faster, and allows us to fix identity parameters for a given subject.

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): “[12] use a hierarchical multiscale approach by computing localized multilinear models on wavelet coefficients.”
Large Scale 3D Morphable Models (2017, methodology): “Similarly toBrunton et al. (2014b),ZulqarnainGilani et al. (2015), a simple model fitting is employed, which consists of”
A 3D Morphable Model Learnt from 10,000 Faces (2016, background): “their recent works, modeling 3D face shapes of different subjects in neutral expression [14] as well as 3D shapes of different subjects in different expressions [12, 9].”
3D Morphable Face Models—Past, Present, and Future (2019, unknown): “To allow modeling localized variations, the multilinear model has been applied to wavelet coefficients at different levels of detail [Brunton et al. 2014a].”
Learning a model of facial shape and expression from 4D scans (2017, methodology): “These measurements have previously been used to evaluate statistical models of various classes of objects, including 3D faces (e.g. [Bolkart and Wuhrer 2015; Booth et al. 2017; Brunton et al. 2014]).”
Modeling Facial Geometry Using Compositional VAEs (2018, background): “[4] rely on many localized multilinear models to reconstruct faces from noisy or occluded point cloud data.”