Facial recognition using deep convolutional neural networks relies on the availability of large datasets of face images. Many examples of identities are needed, and for each identity, a large variety of images are needed in order for the network to learn robustness to intra-class variation. In practice, such datasets are difficult to obtain, particularly those containing adequate variation of pose. Generative Adversarial Networks (GANs) provide a potential solution to this problem due to their ability to generate realistic, synthetic images. However, recent studies have shown that current methods of disentangling pose from identity are inadequate. In this work we incorporate a 3D morphable model into the generator of a GAN in order to learn a nonlinear texture model from in-the-wild images. This allows generation of new, synthetic identities, and manipulation of pose, illumination and expression without compromising the identity. Our synthesised data is used to augment training of facial recognition networks with performance evaluated on the challenging CFP and CPLFW datasets.
翻译:利用深卷变神经网络进行反向认知取决于能否获得大量脸部图像数据集。许多身份实例是需要的。对于每个身份,需要大量的图像,以便网络学习稳健性与阶级内部差异。在实践中,这类数据集很难获得,特别是包含充分变形的数据集。基因反向网络(GANs)由于能够生成现实的合成图像,为这一问题提供了潜在的解决办法。然而,最近的研究表明,目前使身份成形的变异方法不够充分。在这项工作中,我们将3D变形模型纳入GAN生成器,以便学习来自本部图像的非线性纹理模型。这样可以生成新的合成特性,并操纵面部、照明和表达,同时又不损害身份。我们的综合数据被用于加强面部识别网络的培训,对具有挑战性的 CFP 和 CPLFW 数据集的性能进行评估。