A 3D GAN for Improved Large-pose Facial Recognition

  title={A 3D GAN for Improved Large-pose Facial Recognition},
  author={Richard T. Marriott and Sami Romdhani and Liming Chen},
  journal={2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
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… Expand

Figures and Tables from this paper

On the use of automatically generated synthetic image datasets for benchmarking face recognition
This paper introduces the proposed methodology to generate a synthetic dataset, without the need for human intervention, by exploiting the latent structure of a StyleGAN2 model with multiple controlled factors of variation, and confirms that the generated synthetic identities are not data subjects from the GAN's training dataset. Expand
Unsupervised High-Fidelity Facial Texture Generation and Reconstruction
This paper proposes a novel unified pipeline for both tasks, generation of both geometry and texture, and recovery of high-fidelity texture, believed to be the first such unified framework independent of scanned textures. Expand


Reconstruction-Based Disentanglement for Pose-Invariant Face Recognition
This paper presents a method for learning a feature representation that is invariant to pose, without requiring extensive pose coverage in training data, and proposes a new feature reconstruction metric learning to explicitly disentangle identity and pose. Expand
GANFIT: Generative Adversarial Network Fitting for High Fidelity 3D Face Reconstruction
This paper utilizes GANs to train a very powerful generator of facial texture in UV space and revisits the original 3D Morphable Models (3DMMs) fitting approaches making use of non-linear optimization to find the optimal latent parameters that best reconstruct the test image but under a new perspective. Expand
UV-GAN: Adversarial Facial UV Map Completion for Pose-Invariant Face Recognition
A framework for training Deep Convolutional Neural Network (DCNN) to complete the facial UV map extracted from in-the-wild images, and devise a meticulously designed architecture that combines local and global adversarial DCNNs to learn an identity-preserving facial UV completion model. Expand
Dual-Agent GANs for Photorealistic and Identity Preserving Profile Face Synthesis
Experimental results show that the proposed Dual-Agent Generative Adversarial Network (DA-GAN) model not only presents compelling perceptual results but also significantly outperforms state-of-the-arts on the large-scale and challenging NIST IJB-A unconstrained face recognition benchmark. Expand
Dataset Augmentation for Pose and Lighting Invariant Face Recognition
Various methods of incorporating the semi-synthetic renderings into the training procedure of a state of the art deep neural network-based recognition system without modifying the structure of the network itself are investigated. Expand
Synthesizing Coupled 3D Face Modalities by Trunk-Branch Generative Adversarial Networks
This paper presents the first methodology that generates high-quality texture, shape, and normals jointly jointly, which can be used for photo-realistic synthesis and proposes a novel GAN that can generate data from different modalities while exploiting their correlations. Expand
Data augmentation for face recognition
Five data augmentation methods dedicated to face images are proposed, including landmark perturbation and four synthesis methods (hairstyles, glasses, poses, illuminations), which effectively enlarge the training dataset, which alleviates the impacts of misalignment, pose variance, illumination changes and partial occlusions. Expand
Training Deep Face Recognition Systems with Synthetic Data
This work explores how synthetically generated data can be used to decrease the number of real-world images needed for training deep face recognition systems, and makes use of a 3D morphable face model for the generation of images with arbitrary amounts of facial identities and with full control over image variations. Expand
An Assessment of GANs for Identity-related Applications
A state of the art biometric network is applied to various datasets of synthetic images and it is concluded that GANs can indeed be used to generate new, imagined identities meaning that applications such as anonymisation of image sets and augmentation of training datasets with distractor images are viable applications. Expand
Semi-supervised Adversarial Learning to Generate Photorealistic Face Images of New Identities from 3D Morphable Model
A novel end-to-end semi-supervised adversarial framework to generate photorealistic face images of new identities with wide ranges of expressions, poses, and illuminations conditioned by a 3D morphable model achieves comparable results to the state-of-the-art. Expand