Towards Large-Pose Face Frontalization in the Wild
Xi Yin,Xiang Yu,Kihyuk Sohn,Xiaoming Liu,Manmohan Chandraker +4 more
- pp 4010-4019
Reads0
Chats0
TLDR
Zhang et al. as discussed by the authors proposed FF-GAN, a 3DMM-conditioned face frontalization GAN, which employs not only the discriminator and generator loss but also a new masked symmetry loss to retain visual quality under occlusions, besides an identity loss to recover high frequency information.Abstract:
Despite recent advances in face recognition using deep learning, severe accuracy drops are observed for large pose variations in unconstrained environments. Learning pose-invariant features is one solution, but needs expensively labeled large-scale data and carefully designed feature learning algorithms. In this work, we focus on frontalizing faces in the wild under various head poses, including extreme profile view's. We propose a novel deep 3D Morphable Model (3DMM) conditioned Face Frontalization Generative Adversarial Network (GAN), termed as FF-GAN, to generate neutral head pose face images. Our framework differs from both traditional GANs and 3DMM based modeling. Incorporating 3DMM into the GAN structure provides shape and appearance priors for fast convergence with less training data, while also supporting end-to-end training. The 3DMM-conditioned GAN employs not only the discriminator and generator loss but also a new masked symmetry loss to retain visual quality under occlusions, besides an identity loss to recover high frequency information. Experiments on face recognition, landmark localization and 3D reconstruction consistently show the advantage of our frontalization method on faces in the wild datasets. 1read more
Citations
More filters
Proceedings ArticleDOI
Interpreting the Latent Space of GANs for Semantic Face Editing
TL;DR: This work proposes a novel framework, called InterFaceGAN, for semantic face editing by interpreting the latent semantics learned by GANs, and finds that the latent code of well-trained generative models actually learns a disentangled representation after linear transformations.
Posted Content
Interpreting the Latent Space of GANs for Semantic Face Editing
TL;DR: InterFaceGAN as discussed by the authors explores the disentanglement between various semantics and manage to decouple some entangled semantics with subspace projection, leading to more precise control of facial attributes, including gender, age, expression, and the presence of eyeglasses.
Proceedings ArticleDOI
Feature Transfer Learning for Face Recognition With Under-Represented Data
TL;DR: A center-based feature transfer framework to augment the feature space of under-represented subjects from the regular subjects that have sufficiently diverse samples, which presents smooth visual interpolation, which conducts disentanglement to preserve identity of a class while augmenting its feature space with non-identity variations such as pose and lighting.
Proceedings ArticleDOI
Nonlinear 3D Face Morphable Model
Luan Tran,Xiaoming Liu +1 more
TL;DR: This paper proposes an innovative framework to learn a nonlinear 3DMM model from a large set of unconstrained face images, without collecting 3D face scans, and demonstrates the superior representation power of the nonlinear 2D Morphable Model over its linear counterpart.
Journal ArticleDOI
Multi-Task Convolutional Neural Network for Pose-Invariant Face Recognition
Xi Yin,Xiaoming Liu +1 more
TL;DR: A dynamic-weighting scheme to automatically assign the loss weights to each side task solves the crucial problem of balancing between different tasks in MTL and achieves comparable or better performance on LFW, CFP, and IJB-A datasets.
References
More filters
Journal ArticleDOI
Generative Adversarial Nets
Ian Goodfellow,Jean Pouget-Abadie,Mehdi Mirza,Bing Xu,David Warde-Farley,Sherjil Ozair,Aaron Courville,Yoshua Bengio +7 more
TL;DR: A new framework for estimating generative models via an adversarial process, in which two models are simultaneously train: a generative model G that captures the data distribution and a discriminative model D that estimates the probability that a sample came from the training data rather than G.
Posted Content
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
TL;DR: This work introduces a class of CNNs called deep convolutional generative adversarial networks (DCGANs), that have certain architectural constraints, and demonstrates that they are a strong candidate for unsupervised learning.
Labeled Faces in the Wild: A Database forStudying Face Recognition in Unconstrained Environments
TL;DR: The database contains labeled face photographs spanning the range of conditions typically encountered in everyday life, and exhibits “natural” variability in factors such as pose, lighting, race, accessories, occlusions, and background.
Proceedings Article
InfoGAN: interpretable representation learning by information maximizing generative adversarial nets
TL;DR: InfoGAN as mentioned in this paper is an information-theoretic extension to the GAN that is able to learn disentangled representations in a completely unsupervised manner, and it also discovers visual concepts that include hair styles, presence of eyeglasses, and emotions on the CelebA face dataset.
Proceedings ArticleDOI
Supervised Descent Method and Its Applications to Face Alignment
TL;DR: A Supervised Descent Method (SDM) is proposed for minimizing a Non-linear Least Squares (NLS) function and achieves state-of-the-art performance in the problem of facial feature detection.