scholarly journals Mask-aware photorealistic facial attribute manipulation

2021 ◽  
Author(s):  
Ruoqi Sun ◽  
Chen Huang ◽  
Hengliang Zhu ◽  
Lizhuang Ma
Keyword(s):  
Face Recognition ◽  
Experimental Results ◽  
Global Information ◽  
Image Generation ◽  
Feature Maps ◽  
High Quality ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Variational Autoencoder

AbstractThe technique of facial attribute manipulation has found increasing application, but it remains challenging to restrict editing of attributes so that a face’s unique details are preserved. In this paper, we introduce our method, which we call a mask-adversarial autoencoder (M-AAE). It combines a variational autoencoder (VAE) and a generative adversarial network (GAN) for photorealistic image generation. We use partial dilated layers to modify a few pixels in the feature maps of an encoder, changing the attribute strength continuously without hindering global information. Our training objectives for the VAE and GAN are reinforced by supervision of face recognition loss and cycle consistency loss, to faithfully preserve facial details. Moreover, we generate facial masks to enforce background consistency, which allows our training to focus on the foreground face rather than the background. Experimental results demonstrate that our method can generate high-quality images with varying attributes, and outperforms existing methods in detail preservation.

scholarly journals Criminal Face Recognition Using GAN

2020 ◽  
Vol 5 (6) ◽  
pp. 1526-1528
Author(s):  
Anitta George ◽  
Krishnendu K A ◽  
Anusree K ◽  
Adira Suresh Nair ◽  
Hari Shree
Keyword(s):  
Face Recognition ◽  
Learning Approach ◽  
Security Measures ◽  
High Quality ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Machine Learning Approach ◽  
Artificial Image ◽  
The Given ◽  
Biometric Feature

Forensics and security at present often use low technological resources. Security measures often fail to update with the upcoming technology. This project is based on implementing an automatic face recognition of criminals or specific targets using machine-learning approach. Given a set of features to a Generative Adversarial Network(GAN), the algorithm generates an image of the target with the specified feature set. The input to the machine can either be a given set of features or a set of portraits varying from frontals to side profiles from which these features can be extracted. The accuracy of the system is directly proportional to the number of epochs trained in the network. The generated output image can vary from primitive, low resolution images to high quality images where features are more recognizable. This is then compared with a predefined database of existing people. Thus, the target can immediately be recognized with the generation of an artificial image with the given biometric feature set, which will be again compared by a discriminator network to check the true identity of the target.

scholarly journals A Character-Centric Neural Model for Automated Story Generation

2020 ◽  
Vol 34 (02) ◽  
pp. 1725-1732 ◽  
Author(s):  
Danyang Liu ◽  
Juntao Li ◽  
Meng-Hsuan Yu ◽  
Ziming Huang ◽  
Gongshen Liu ◽  
...  
Keyword(s):  
Neural Networks ◽  
Prior Knowledge ◽  
Neural Model ◽  
Experimental Results ◽  
Generative Adversarial Network ◽  
Story Generation ◽  
Adversarial Network ◽  
Variational Autoencoder ◽  
Linguistic Patterns ◽  
The Given

Automated story generation is a challenging task which aims to automatically generate convincing stories composed of successive plots correlated with consistent characters. Most recent generation models are built upon advanced neural networks, e.g., variational autoencoder, generative adversarial network, convolutional sequence to sequence model. Although these models have achieved prompting results on learning linguistic patterns, very few methods consider the attributes and prior knowledge of the story genre, especially from the perspectives of explainability and consistency. To fill this gap, we propose a character-centric neural storytelling model, where a story is created encircling the given character, i.e., each part of a story is conditioned on a given character and corresponded context environment. In this way, we explicitly capture the character information and the relations between plots and characters to improve explainability and consistency. Experimental results on open dataset indicate that our model yields meaningful improvements over several strong baselines on both human and automatic evaluations.

scholarly journals An Underwater Image Enhancement Algorithm Based on Generative Adversarial Network and Natural Image Quality Evaluation Index

2021 ◽  
Vol 9 (7) ◽  
pp. 691
Author(s):  
Kai Hu ◽  
Yanwen Zhang ◽  
Chenghang Weng ◽  
Pengsheng Wang ◽  
Zhiliang Deng ◽  
...  
Keyword(s):  
Image Quality ◽  
Image Enhancement ◽  
Quality Evaluation ◽  
High Efficiency ◽  
Natural Image ◽  
High Quality ◽  
Generative Adversarial Network ◽  
Image Quality Evaluation ◽  
Adversarial Network ◽  
Underwater Image

When underwater vehicles work, underwater images are often absorbed by light and scattered and diffused by floating objects, which leads to the degradation of underwater images. The generative adversarial network (GAN) is widely used in underwater image enhancement tasks because it can complete image-style conversions with high efficiency and high quality. Although the GAN converts low-quality underwater images into high-quality underwater images (truth images), the dataset of truth images also affects high-quality underwater images. However, an underwater truth image lacks underwater image enhancement, which leads to a poor effect of the generated image. Thus, this paper proposes to add the natural image quality evaluation (NIQE) index to the GAN to provide generated images with higher contrast and make them more in line with the perception of the human eye, and at the same time, grant generated images a better effect than the truth images set by the existing dataset. In this paper, several groups of experiments are compared, and through the subjective evaluation and objective evaluation indicators, it is verified that the enhanced image of this algorithm is better than the truth image set by the existing dataset.

scholarly journals CDL-GAN: Contrastive Distance Learning Generative Adversarial Network for Image Generation

2021 ◽  
Vol 11 (4) ◽  
pp. 1380
Author(s):  
Yingbo Zhou ◽  
Pengcheng Zhao ◽  
Weiqin Tong ◽  
Yongxin Zhu
Keyword(s):  
Distance Learning ◽  
Feature Learning ◽  
Image Synthesis ◽  
Image Feature ◽  
Generative Adversarial Networks ◽  
Image Generation ◽  
Generative Adversarial Network ◽  
Feature Representations ◽  
Adversarial Network ◽  
Public Datasets

While Generative Adversarial Networks (GANs) have shown promising performance in image generation, they suffer from numerous issues such as mode collapse and training instability. To stabilize GAN training and improve image synthesis quality with diversity, we propose a simple yet effective approach as Contrastive Distance Learning GAN (CDL-GAN) in this paper. Specifically, we add Consistent Contrastive Distance (CoCD) and Characteristic Contrastive Distance (ChCD) into a principled framework to improve GAN performance. The CoCD explicitly maximizes the ratio of the distance between generated images and the increment between noise vectors to strengthen image feature learning for the generator. The ChCD measures the sampling distance of the encoded images in Euler space to boost feature representations for the discriminator. We model the framework by employing Siamese Network as a module into GANs without any modification on the backbone. Both qualitative and quantitative experiments conducted on three public datasets demonstrate the effectiveness of our method.

Does Generative Adversarial Network (GAN) help in SRAF image generation?

2021 ◽  
Author(s):  
Jialu Huang ◽  
Ying Huang ◽  
Yan-ting Lin ◽  
Zi-yang Liu ◽  
Yang Lin ◽  
...  
Keyword(s):  
Image Generation ◽  
Generative Adversarial Network ◽  
Adversarial Network

Technique for Removing Unnecessary Superimposed Patterns from Image using Generative Network

2021 ◽  
Author(s):  
Kazutake Uehira ◽  
Hiroshi Unno
Keyword(s):  
Color Image ◽  
Depth Map ◽  
Experimental Results ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Blue Component ◽  
Component Image

A technique for removing unnecessary patterns from captured images by using a generative network is studied. The patterns, composed of lines and spaces, are superimposed onto a blue component image of RGB color image when the image is captured for the purpose of acquiring a depth map. The superimposed patterns become unnecessary after the depth map is acquired. We tried to remove these unnecessary patterns by using a generative adversarial network (GAN) and an auto encoder (AE). The experimental results show that the patterns can be removed by using a GAN and AE to the point of being invisible. They also show that the performance of GAN is much higher than that of AE and that its PSNR and SSIM were over 45 and about 0.99, respectively. From the results, we demonstrate the effectiveness of the technique with a GAN.

scholarly journals WHITE-BOX CARTOONIZATION USING AN EXTENDED GAN FRAMEWORK

2021 ◽  
Vol 5 (12) ◽  
Author(s):  
Amey Thakur ◽  
Hasan Rizvi ◽  
Mega Satish
Keyword(s):  
Smooth Surface ◽  
Generative Models ◽  
Surface Representation ◽  
High Quality ◽  
Generative Adversarial Network ◽  
Structure Representation ◽  
Texture Representation ◽  
Adversarial Network ◽  
Representation Structure ◽  
New Framework

In the present study, we propose to implement a new framework for estimating generative models via an adversarial process to extend an existing GAN framework and develop a white-box controllable image cartoonization, which can generate high-quality cartooned images/videos from real-world photos and videos. The learning purposes of our system are based on three distinct representations: surface representation, structure representation, and texture representation. The surface representation refers to the smooth surface of the images. The structure representation relates to the sparse colour blocks and compresses generic content. The texture representation shows the texture, curves, and features in cartoon images. Generative Adversarial Network (GAN) framework decomposes the images into different representations and learns from them to generate cartoon images. This decomposition makes the framework more controllable and flexible which allows users to make changes based on the required output. This approach overcomes any previous system in terms of maintaining clarity, colours, textures, shapes of images yet showing the characteristics of cartoon images.

Sign in / Sign up

Export Citation Format

Share Document