Gaussian mixture 3D morphable face model

Koppen, Paul; Feng, Zhen-Hua; Kittler, Josef; Awais, Muhammad; Christmas, William J.; Wu, Xiao-Jun; Yin, He-Feng

doi:10.1016/j.patcog.2017.09.006

Cited by 74 publications

(38 citation statements)

References 46 publications

(43 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A facial landmark usually has specific semantic meaning, e.g. nose tip or eye centre, which provides rich geometric information for other face analysis tasks such as face recognition [57,42,39,69], emotion estimation [71,16,59,37] and 3D face reconstruction [15,33,28,27,50,35,19].…”

Section: Introductionmentioning

confidence: 99%

Wing Loss for Robust Facial Landmark Localisation with Convolutional Neural Networks

Feng

Kittler

Awais

et al. 2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

Self Cite

357

212

View full text Add to dashboard Cite

We present a new loss function, namely Wing loss, for robust facial landmark localisation with Convolutional Neural Networks (CNNs). We first compare and analyse different loss functions including L2, L1 and smooth L1. The analysis of these loss functions suggests that, for the training of a CNN-based localisation model, more attention should be paid to small and medium range errors. To this end, we design a piece-wise loss function. The new loss amplifies the impact of errors from the interval (-w, w) by switching from L1 loss to a modified logarithm function.To address the problem of under-representation of samples with large out-of-plane head rotations in the training set, we propose a simple but effective boosting strategy, referred to as pose-based data balancing. In particular, we deal with the data imbalance problem by duplicating the minority training samples and perturbing them by injecting random image rotation, bounding box translation and other data augmentation approaches. Last, the proposed approach is extended to create a two-stage framework for robust facial landmark localisation. The experimental results obtained on AFLW and 300W demonstrate the merits of the Wing loss function, and prove the superiority of the proposed method over the state-of-the-art approaches.

show abstract

Section: Introductionmentioning

confidence: 99%

Wing Loss for Robust Facial Landmark Localisation with Convolutional Neural Networks

Feng

Kittler

Awais

et al. 2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

Self Cite

357

212

View full text Add to dashboard Cite

show abstract

“…The concept of Gaussian Process Morphable Models (GPMMs) was recently introduced in [22,14,18]. The main contribution of GPMMs is the generalization of classic Point Distribution Models (such as are constructed using PCA), with the help of Gaussian processes.…”

Section: Gaussian Process Modelingmentioning

confidence: 99%

Combining 3D Morphable Models: A Large Scale Face-And-Head Model

Ploumpis

Wang

Pears

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

framework to blend covariance matrices from multiple models. Second, as an example application of our approach, we build a new face-and-head shape model that combines the variability and facial detail of the LSFM with the full head modelling of the LYHM. The resulting combined shape model achieves state-of-the-art performance and outperforms existing head models by a large margin. Finally, as an application experiment, we reconstruct full head representations from single, unconstrained images by utilizing our proposed large-scale model in conjunction with the Face-Warehouse blendshapes for handling expressions.

show abstract

“…However, facial variations are nonlinear in the real world, e.g., the variations in different facial expressions. Although some recent works [7,6,5,27,23] are proposed to improve statistical models, they still construct the 3D face shape by linearly combining the basis.…”

Section: Introductionmentioning

confidence: 99%

Disentangled Representation Learning for 3D Face Shape

Jiang

Chen

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

101

View full text Add to dashboard Cite

In this paper, we present a novel strategy to design disentangled 3D face shape representation. Specifically, a given 3D face shape is decomposed into identity part and expression part, which are both encoded in a nonlinear way. To solve this problem, we propose an attribute decomposition framework for 3D face mesh. To better represent face shapes which are usually nonlinear deformed between each other, the face shapes are represented by a vertex based deformation representation rather than Euclidean coordinates. The experimental results demonstrate that our method has better performance than existing methods on decomposing the identity and expression parts. Moreover, more natural expression transfer results can be achieved with our method than existing methods.

show abstract

Gaussian mixture 3D morphable face model

Cited by 74 publications

References 46 publications

Wing Loss for Robust Facial Landmark Localisation with Convolutional Neural Networks

Wing Loss for Robust Facial Landmark Localisation with Convolutional Neural Networks

Combining 3D Morphable Models: A Large Scale Face-And-Head Model

Disentangled Representation Learning for 3D Face Shape

Contact Info

Product

Resources

About