scholarly journals FRGAN: A Blind Face Restoration with Generative Adversarial Networks

2021 ◽  
Vol 2021 ◽  
pp. 1-14
Author(s):  
Tongxin Wei ◽  
Qingbao Li ◽  
Zhifeng Chen ◽  
Jinjin Liu
Keyword(s):  
Activation Function ◽  
Human Motion ◽  
Face Image ◽  
Head Pose Estimation ◽  
Generative Adversarial Networks ◽  
3D Face Reconstruction ◽  
Adversarial Networks ◽  
The Face ◽  
In The Wild ◽  
Facial Images

Recent works based on deep learning and facial priors have performed well in superresolving severely degraded facial images. However, due to the limitation of illumination, pixels of the monitoring probe itself, focusing area, and human motion, the face image is usually blurred or even deformed. To address this problem, we properly propose Face Restoration Generative Adversarial Networks to improve the resolution and restore the details of the blurred face. They include the Head Pose Estimation Network, Postural Transformer Network, and Face Generative Adversarial Networks. In this paper, we employ the following: (i) Swish-B activation function that is used in Face Generative Adversarial Networks to accelerate the convergence speed of the cross-entropy cost function, (ii) a special prejudgment monitor that is added to improve the accuracy of the discriminant, and (iii) the modified Postural Transformer Network that is used with 3D face reconstruction network to correct faces at different expression pose angles. Our method improves the resolution of face image and performs well in image restoration. We demonstrate how our method can produce high-quality faces, and it is superior to the most advanced methods on the reconstruction task of blind faces for in-the-wild images; especially, our 8 × SR SSIM and PSNR are, respectively, 0.078 and 1.16 higher than FSRNet in AFLW.

Towards Accuracy Enhancement of Age Group Classification Using Generative Adversarial Networks

2021 ◽  
pp. 1-17
Author(s):  
Khaled ELKarazle ◽  
Valliappan Raman ◽  
Patrick Then
Keyword(s):  
Age Estimation ◽  
Super Resolution ◽  
Generative Adversarial Networks ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Adversarial Networks ◽  
Original Dataset ◽  
Age Group Classification ◽  
Facial Images

Age estimation models can be employed in many applications, including soft biometrics, content access control, targeted advertising, and many more. However, as some facial images are taken in unrestrained conditions, the quality relegates, which results in the loss of several essential ageing features. This study investigates how introducing a new layer of data processing based on a super-resolution generative adversarial network (SRGAN) model can influence the accuracy of age estimation by enhancing the quality of both the training and testing samples. Additionally, we introduce a novel convolutional neural network (CNN) classifier to distinguish between several age classes. We train one of our classifiers on a reconstructed version of the original dataset and compare its performance with an identical classifier trained on the original version of the same dataset. Our findings reveal that the classifier which trains on the reconstructed dataset produces better classification accuracy, opening the door for more research into building data-centric machine learning systems.

scholarly journals Generation of Facial Drawings Using Generative Adversarial Networks

2019 ◽  
Vol 8 (6) ◽  
pp. 746-750
Keyword(s):  
Research Work ◽  
Generative Adversarial Networks ◽  
Legal Proceedings ◽  
Video Footage ◽  
Basic Model ◽  
Adversarial Networks ◽  
Generative Algorithms ◽  
Facial Images

Facial sketches are widely used in judicial and legal proceedings. Law enforcers use facial sketches to help them with the visual aspects of the case, using witness descriptions and video footage. However, drawing forensic sketches by hand is a time-consuming procedure and a situation may arise where the authorities have less time in hand to solve a case. The present research work aims to create a basic model which can generate facial images from a given set of input features; similar to what a forensic artist does, thus, enabling a faster and efficient sketching procedure. In this work, a category of generative algorithms, called Generative Adversarial Networks has been used to build this model. To train this model, a dataset of anime girls has been used and thus it can only generate the same, making sure that the generated image contains the input features.

scholarly journals RoCGAN: Robust Conditional GAN

2020 ◽  
Vol 128 (10-11) ◽  
pp. 2665-2683 ◽  
Author(s):  
Grigorios G. Chrysos ◽  
Jean Kossaifi ◽  
Stefanos Zafeiriou
Keyword(s):  
Large Scale ◽  
Real Data ◽  
Superior Performance ◽  
Target Space ◽  
Generative Adversarial Networks ◽  
Natural Scenes ◽  
Adversarial Networks ◽  
Target Manifold ◽  
The Face ◽  
Intense Noise

Abstract Conditional image generation lies at the heart of computer vision and conditional generative adversarial networks (cGAN) have recently become the method of choice for this task, owing to their superior performance. The focus so far has largely been on performance improvement, with little effort in making cGANs more robust to noise. However, the regression (of the generator) might lead to arbitrarily large errors in the output, which makes cGANs unreliable for real-world applications. In this work, we introduce a novel conditional GAN model, called RoCGAN, which leverages structure in the target space of the model to address the issue. Specifically, we augment the generator with an unsupervised pathway, which promotes the outputs of the generator to span the target manifold, even in the presence of intense noise. We prove that RoCGAN share similar theoretical properties as GAN and establish with both synthetic and real data the merits of our model. We perform a thorough experimental validation on large scale datasets for natural scenes and faces and observe that our model outperforms existing cGAN architectures by a large margin. We also empirically demonstrate the performance of our approach in the face of two types of noise (adversarial and Bernoulli).

scholarly journals Age Progression and Regression with Spatial Attention Modules

2020 ◽  
Vol 34 (07) ◽  
pp. 11378-11385
Author(s):  
Qi Li ◽  
Yunfan Liu ◽  
Zhenan Sun
Keyword(s):  
Spatial Attention ◽  
Generative Adversarial Networks ◽  
Age Progression ◽  
Training Images ◽  
Adversarial Networks ◽  
Face Images ◽  
Multiple Datasets ◽  
Image Translation ◽  
In The Wild ◽  
Face Aging

Age progression and regression refers to aesthetically rendering a given face image to present effects of face aging and rejuvenation, respectively. Although numerous studies have been conducted in this topic, there are two major problems: 1) multiple models are usually trained to simulate different age mappings, and 2) the photo-realism of generated face images is heavily influenced by the variation of training images in terms of pose, illumination, and background. To address these issues, in this paper, we propose a framework based on conditional Generative Adversarial Networks (cGANs) to achieve age progression and regression simultaneously. Particularly, since face aging and rejuvenation are largely different in terms of image translation patterns, we model these two processes using two separate generators, each dedicated to one age changing process. In addition, we exploit spatial attention mechanisms to limit image modifications to regions closely related to age changes, so that images with high visual fidelity could be synthesized for in-the-wild cases. Experiments on multiple datasets demonstrate the ability of our model in synthesizing lifelike face images at desired ages with personalized features well preserved, and keeping age-irrelevant regions unchanged.

BPA-GAN: Human Motion Transfer Using Body-Part-Aware Generative Adversarial Networks

2021 ◽  
pp. 101107
Author(s):  
Jinfeng Jiang ◽  
Guiqing Li ◽  
Shihao Wu ◽  
Huiqian Zhang ◽  
Yongwei Nie
Keyword(s):  
Body Part ◽  
Human Motion ◽  
Generative Adversarial Networks ◽  
Adversarial Networks

Multi-pose 3D facial texture refinement for face recognition

2018 ◽  
Vol 16 (02) ◽  
pp. 1840006
Author(s):  
Wanshun Gao ◽  
Xi Zhao ◽  
Jun An ◽  
Jianhua Zou
Keyword(s):  
Face Recognition ◽  
State Of The Art ◽  
Competitive Performance ◽  
3D Face Reconstruction ◽  
3D Face ◽  
Face Reconstruction ◽  
Novel Approach ◽  
Art Methods ◽  
The Face ◽  
Facial Images

In this paper, we propose a novel approach for 3D face reconstruction from multi-facial images. Given original pose-variant images, coarse 3D face templates are initialized to reconstruct a refined 3D face mesh in an iteration manner. Then, we warp original facial images to the 2D meshes projected from 3D using Sparse Mesh Affine Warp (SMAW). Finally, we weight the face patches in each view respectively and map the patch with higher weight to a canonical UV space. For facial images with arbitrary pose, their invisible regions are filled with the corresponding UV patches. Poisson editing is applied to blend different patches seamlessly. We evaluate the proposed method on LFW dataset in terms of texture refinement and face recognition. The results demonstrate competitive performance compared to state-of-the-art methods.

scholarly journals FT-GAN: Face Transformation with Key Points Alignment for Pose-Invariant Face Recognition

Electronics ◽  
2019 ◽  
Vol 8 (7) ◽  
pp. 807 ◽  
Author(s):  
Weiwei Zhuang ◽  
Liang Chen ◽  
Chaoqun Hong ◽  
Yuxin Liang ◽  
Keshou Wu
Keyword(s):  
Face Recognition ◽  
Generative Adversarial Networks ◽  
Facial Features ◽  
Adversarial Networks ◽  
Key Points ◽  
In The Wild ◽  
Novel Method ◽  
Face Synthesis ◽  
Unconstrained Face

Face recognition has been comprehensively studied. However, face recognition in the wild still suffers from unconstrained face directions. Frontal face synthesis is a popular solution, but some facial features are missed after synthesis. This paper presents a novel method for pose-invariant face recognition. It is based on face transformation with key points alignment based on generative adversarial networks (FT-GAN). In this method, we introduce CycleGAN for pixel transformation to achieve coarse face transformation results, and these results are refined by key point alignment. In this way, frontal face synthesis is modeled as a two-task process. The results of comprehensive experiments show the effectiveness of FT-GAN.

scholarly journals Weakly Supervised GAN for Image-to-Image Translation in the Wild

2020 ◽  
Vol 2020 ◽  
pp. 1-8
Author(s):  
Zhiyi Cao ◽  
Shaozhang Niu ◽  
Jiwei Zhang
Keyword(s):  
Generative Adversarial Networks ◽  
Adversarial Networks ◽  
Image Translation ◽  
Latent Space ◽  
In The Wild ◽  
Adversarial Examples ◽  
Weakly Supervised ◽  
Public Datasets ◽  
Global And Local ◽  
The Given

Generative Adversarial Networks (GANs) have achieved significant success in unsupervised image-to-image translation between given categories (e.g., zebras to horses). Previous GANs models assume that the shared latent space between different categories will be captured from the given categories. Unfortunately, besides the well-designed datasets from given categories, many examples come from different wild categories (e.g., cats to dogs) holding special shapes and sizes (short for adversarial examples), so the shared latent space is troublesome to capture, and it will cause the collapse of these models. For this problem, we assume the shared latent space can be classified as global and local and design a weakly supervised Similar GANs (Sim-GAN) to capture the local shared latent space rather than the global shared latent space. For the well-designed datasets, the local shared latent space is close to the global shared latent space. For the wild datasets, we will get the local shared latent space to stop the model from collapse. Experiments on four public datasets show that our model significantly outperforms state-of-the-art baseline methods.

Sign in / Sign up

Export Citation Format

Share Document