Representation Learning by Rotating Your Faces

Tran, Luan; Yin, Xi; Liu, Xiaoming

doi:10.1109/tpami.2018.2868350

Cited by 136 publications

(88 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(v) DR-GAN: Proposed by a team from Michigan State University, USA, the framework performs face detection and alignment on the input images using MT-CNN [33]. This is followed by feature extraction using the Disentangled Representation learning-Generative Adversarial Network (DR-GAN) [38]. Classification is performed using Cosine distance.…”

Section: (Iii) Deep Disguise Recognizer Network (Ddrnet) [27]mentioning

confidence: 99%

Recognizing Disguised Faces in the Wild

Singh

Vatsa

et al. 2019

IEEE Trans. Biom. Behav. Identity Sci.

View full text Add to dashboard Cite

Research in face recognition has seen tremendous growth over the past couple of decades. Beginning from algorithms capable of performing recognition in constrained environments, the current face recognition systems achieve very high accuracies on large-scale unconstrained face datasets. While upcoming algorithms continue to achieve improved performance, a majority of the face recognition systems are susceptible to failure under disguise variations, one of the most challenging covariate of face recognition. In literature, some algorithms demonstrate promising results on existing disguise datasets, however, most of the disguise datasets contain images with limited variations, often captured in controlled settings. This does not simulate a real world scenario, where both intentional and unintentional unconstrained disguises are encountered by a face recognition system. In this paper, a novel Disguised Faces in the Wild (DFW) dataset is proposed which contains over 11,000 images of 1,000 identities with variations across different types of disguise accessories. The dataset is collected from the Internet, resulting in unconstrained face images similar to real world settings. This is the first-of-a-kind dataset with the availability of impersonator and genuine obfuscated face images for each subject. The proposed DFW dataset has been analyzed in terms of three levels of difficulty: (i) easy, (ii) medium, and (iii) hard in order to showcase the challenging nature of the problem. It is our view that the research community can greatly benefit from the DFW dataset in terms of developing algorithms robust to such adversaries. The proposed dataset was released as part of the First International Workshop and Competition on Disguised Faces in the Wild at the International Conference on Computer Vision and Pattern Recognition, 2018. This paper presents the DFW dataset in detail, including the evaluation protocols, baseline results, performance analysis of the submissions received as part of the competition, and three levels of difficulties of the DFW challenge dataset. Index Terms-FaceRecognition, Disguise in the Wild. ! arXiv:1811.08837v1 [cs.CV]

show abstract

Section: (Iii) Deep Disguise Recognizer Network (Ddrnet) [27]mentioning

confidence: 99%

Recognizing Disguised Faces in the Wild

Singh

Vatsa

et al. 2019

IEEE Trans. Biom. Behav. Identity Sci.

View full text Add to dashboard Cite

show abstract

“…In addition to adopting 3D convolutions to learn 3D features, during training, we introduce more bias about the 3D world by transforming these learnt features to random poses before projecting them to 2D images. This random pose transformation is crucial to guarantee that HoloGAN learns a 3D representation that is disentangled and can be rendered from all possible views, as also observed by Tran et al [55] in DR-GAN. However, HoloGAN performs explicit 3D rigid-body transformation, while DR-GAN performs this using an implicit vector representation.…”

Section: Learning With View-dependent Mappingsmentioning

confidence: 92%

HoloGAN: Unsupervised Learning of 3D Representations From Natural Images

Nguyen-Phuoc

Theis

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

338

397

View full text Add to dashboard Cite

Figure 1. HoloGAN learns to separate pose from identity (shape and appearance) only from unlabelled 2D images without sacrificing the visual fidelity of the generated images. All results shown here are sampled from HoloGAN for the same identities in each row but in different poses. AbstractWe propose a novel generative adversarial network (GAN) for the task of unsupervised learning of 3D representations from natural images. Most generative models rely on 2D kernels to generate images and make few assumptions about the 3D world. These models therefore tend to create blurry images or artefacts in tasks that require a strong 3D understanding, such as novel-view synthesis. HoloGAN instead learns a 3D representation of the world, and to render this representation in a realistic manner. Unlike other GANs, HoloGAN provides explicit control over the pose of generated objects through rigid-body transformations of the learnt 3D features. Our experiments show that using explicit 3D features enables HoloGAN to disentangle 3D pose and identity, which is further decomposed into shape and appearance, while still being able to generate images with similar or higher visual quality than other generative models. HoloGAN can be trained end-to-end from unlabelled 2D images only. In particular, we do not require pose labels, 3D shapes, or multiple views of the same objects. This shows that HoloGAN is the first generative model that learns 3D representations from natural images in an entirely unsupervised manner.

show abstract

“…We explore the effect of our proposed 3DMM on preserving identity when reconstructing face images. Using DR-GAN [48], a pretrained face recognition network, we can compute the cosine distance between the input and its reconstruction from different models. Fig.…”

Section: Identity-preservingmentioning

confidence: 99%

Towards High-Fidelity Nonlinear 3D Face Morphable Model

Tran

Liu

2019

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

Self Cite

171

View full text Add to dashboard Cite

Figure 1: With novel enhancements in both learning objective as well as the network architecture, our proposed nonlinear 3D morphable model enables, for the first time, regressing high-fidelity facial shape (geometry) and albedo (skin reflectence) by directly estimating model latent representations. AbstractEmbedding 3 D morphable basis functions into deep neural networks opens great potential for models with better representation power. However, to faithfully learn those models from an image collection, it requires strong regularization to overcome ambiguities involved in the learning process. This critically prevents us from learning high fidelity face models which are needed to represent face images in high level of details. To address this problem, this paper presents a novel approach to learn additional proxies as means to side-step strong regularizations, as well as, leverages to promote detailed shape/albedo. To ease the learning, we also propose to use a dual-pathway network, a carefully-designed architecture that brings a balance between global and local-based models. By improving the nonlinear 3 D morphable model in both learning objective and network architecture, we present a model which is superior in capturing higher level of details than the linear or its precedent nonlinear counterparts. As a result, our model achieves state-of-the-art performance on 3 D face reconstruction by solely optimizing latent representations.

show abstract

Representation Learning by Rotating Your Faces

Cited by 136 publications

References 58 publications

Recognizing Disguised Faces in the Wild

Recognizing Disguised Faces in the Wild

HoloGAN: Unsupervised Learning of 3D Representations From Natural Images

Towards High-Fidelity Nonlinear 3D Face Morphable Model

Contact Info

Product

Resources

About