Proceedings ArticleDOI
Disentangled Representation Learning GAN for Pose-Invariant Face Recognition
Luan Tran,Xi Yin,Xiaoming Liu +2 more
- pp 1283-1292
TLDR
Quantitative and qualitative evaluation on both controlled and in-the-wild databases demonstrate the superiority of DR-GAN over the state of the art.Abstract:
The large pose discrepancy between two face images is one of the key challenges in face recognition. Conventional approaches for pose-invariant face recognition either perform face frontalization on, or learn a pose-invariant representation from, a non-frontal face image. We argue that it is more desirable to perform both tasks jointly to allow them to leverage each other. To this end, this paper proposes Disentangled Representation learning-Generative Adversarial Network (DR-GAN) with three distinct novelties. First, the encoder-decoder structure of the generator allows DR-GAN to learn a generative and discriminative representation, in addition to image synthesis. Second, this representation is explicitly disentangled from other face variations such as pose, through the pose code provided to the decoder and pose estimation in the discriminator. Third, DR-GAN can take one or multiple images as the input, and generate one unified representation along with an arbitrary number of synthetic images. Quantitative and qualitative evaluation on both controlled and in-the-wild databases demonstrate the superiority of DR-GAN over the state of the art.read more
Citations
More filters
Journal ArticleDOI
Deep Facial Expression Recognition: A Survey
Shan Li,Weihong Deng +1 more
TL;DR: A comprehensive survey on deep facial expression recognition (FER) can be found in this article, including datasets and algorithms that provide insights into the intrinsic problems of deep FER, including overfitting caused by lack of sufficient training data and expression-unrelated variations, such as illumination, head pose and identity bias.
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.
Journal ArticleDOI
Deep learning on image denoising: An overview.
TL;DR: A comparative study of deep techniques in image denoising by classifying the deep convolutional neural networks for additive white noisy images, the deep CNNs for real noisy images; the deepCNNs for blind Denoising and the deep network for hybrid noisy images.
Proceedings ArticleDOI
Beyond Face Rotation: Global and Local Perception GAN for Photorealistic and Identity Preserving Frontal View Synthesis
TL;DR: Tang et al. as discussed by the authors proposed a Two-Pathway Generative Adversarial Network (TP-GAN) for photorealistic frontal view synthesis by simultaneously perceiving global structures and local details.
Proceedings ArticleDOI
Learning Deep Models for Face Anti-Spoofing: Binary or Auxiliary Supervision
TL;DR: This paper argues the importance of auxiliary supervision to guide the learning toward discriminative and generalizable cues, and introduces a new face anti-spoofing database that covers a large range of illumination, subject, and pose variations.
References
More filters
Proceedings ArticleDOI
Pose-robust face recognition using geometry assisted probabilistic modeling
Xiaoming Liu,Tsuhan Chen +1 more
TL;DR: A geometry assisted probabilistic approach to improve face recognition under pose variation by approximate a human head with a 3D ellipsoid model, which enables the recognition to be conducted by comparing the texture maps instead of the original images, as done in traditional face recognition.
Proceedings ArticleDOI
Patch-based probabilistic image quality assessment for face selection and improved video-based face recognition
Wong,Chen,Mau,Sanderson,Lovell +4 more
Book ChapterDOI
Morphable displacement field based image matching for face recognition across pose
TL;DR: A novel method, named Morphable Displacement Field (MDF), to match G with P's virtual view under G's pose by formulating MDF as a convex combination of a number of template displacement fields generated from a 3D face database, which satisfies both global conformity and local consistency.
Proceedings ArticleDOI
Random Faces Guided Sparse Many-to-One Encoder for Pose-Invariant Face Recognition
TL;DR: This paper builds a single-hidden-layer neural network with sparse constraint, to extract pose-invariant feature for face recognition in a supervised fashion, and enhances the discriminative capability of the proposed feature by using multiple random faces as the target values for multiple encoders.