scholarly journals Image Translation by Domain-Adversarial Training

2018 ◽  
Vol 2018 ◽  
pp. 1-11 ◽  
Author(s):  
Zhuorong Li ◽  
Wanliang Wang ◽  
Yanwei Zhao
Keyword(s):  
Domain Adaptation ◽  
Input Image ◽  
Generative Adversarial Networks ◽  
Significant Progress ◽  
Mapping Space ◽  
Adversarial Networks ◽  
Image Prior ◽  
Image Translation ◽  
Common Framework ◽  
Adversarial Training

Image translation, where the input image is mapped to its synthetic counterpart, is attractive in terms of wide applications in fields of computer graphics and computer vision. Despite significant progress on this problem, largely due to a surge of interest in conditional generative adversarial networks (cGANs), most of the cGAN-based approaches require supervised data, which are rarely available and expensive to provide. Instead we elaborate a common framework that is also applicable to the unsupervised cases, learning the image prior by conditioning the discriminator on unaligned targets to reduce the mapping space and improve the generation quality. Besides, domain-adversarial training inspired by domain adaptation is proposed to capture discriminative and expressive features, for the purpose of improving fidelity. Effectiveness of our method is demonstrated by compelling experimental results of our method and comparisons with several baselines. As for the generality, it could be analyzed from two perspectives: adaptation to both supervised and unsupervised setting and the diversity of tasks.

scholarly journals Multi-Attribute Transfer via Disentangled Representation

2019 ◽  
Vol 33 ◽  
pp. 9195-9202 ◽  
Author(s):  
Jianfu Zhang ◽  
Yuanyuan Huang ◽  
Yaoyi Li ◽  
Weijie Zhao ◽  
Liqing Zhang
Keyword(s):  
Neural Network ◽  
Facial Expression ◽  
Generative Adversarial Networks ◽  
Significant Progress ◽  
Target Domain ◽  
Adversarial Networks ◽  
Proposed Model ◽  
Image Translation ◽  
Realistic Images ◽  
Novel Model

Recent studies show significant progress in image-to-image translation task, especially facilitated by Generative Adversarial Networks. They can synthesize highly realistic images and alter the attribute labels for the images. However, these works employ attribute vectors to specify the target domain which diminishes image-level attribute diversity. In this paper, we propose a novel model formulating disentangled representations by projecting images to latent units, grouped feature channels of Convolutional Neural Network, to disassemble the information between different attributes. Thanks to disentangled representation, we can transfer attributes according to the attribute labels and moreover retain the diversity beyond the labels, namely, the styles inside each image. This is achieved by specifying some attributes and swapping the corresponding latent units to “swap” the attributes appearance, or applying channel-wise interpolation to blend different attributes. To verify the motivation of our proposed model, we train and evaluate our model on face dataset CelebA. Furthermore, the evaluation of another facial expression dataset RaFD demonstrates the generalizability of our proposed model.

scholarly journals Daydriex: Translating Nighttime Scenes towards Daytime Driving Experience at Night

2021 ◽  
Vol 11 (5) ◽  
pp. 2013
Author(s):  
Euihyeok Lee ◽  
Seungwoo Kang
Keyword(s):  
Input Image ◽  
Generative Adversarial Networks ◽  
User Perception ◽  
Missing Information ◽  
High Quality ◽  
Driving Experience ◽  
Processing Pipeline ◽  
Adversarial Networks ◽  
Image Translation ◽  
Translation Techniques

What if the window of our cars is a magic window, which transforms dark views outside of the window at night into bright ones as we can see in the daytime? To realize such a window, one of important requirements is that the stream of transformed images displayed on the window should be of high quality so that users perceive it as real scenes in the day. Although image-to-image translation techniques based on Generative Adversarial Networks (GANs) have been widely studied, night-to-day image translation is still a challenging task. In this paper, we propose Daydriex, a processing pipeline to generate enhanced daytime translation focusing on road views. Our key idea is to supplement the missing information in dark areas of input image frames by using existing daytime images corresponding to the input images from street view services. We present a detailed processing flow and address several issues to realize our idea. Our evaluation shows that the results by Daydriex achieves lower Fréchet Inception Distance (FID) scores and higher user perception scores compared to those by CycleGAN only.

scholarly journals Unpaired Image- to- Image Translation using Cycle Generative Adversarial Networks

2020 ◽  
Vol 9 (6) ◽  
pp. 380-385
Keyword(s):  
Mapping Function ◽  
Image Synthesis ◽  
Input Image ◽  
General Purpose ◽  
Training Dataset ◽  
Generative Adversarial Networks ◽  
Inverse Mapping ◽  
Style Transfer ◽  
Adversarial Networks ◽  
Image Translation

In this burgeoning age and society where people are tending towards learning the benefits adversarial network we hereby benefiting the society tend to extend our research towards adversarial networks as a general-purpose solution to image-to-image translation problems. Image to image translation comes under the peripheral class of computer sciences extending our branch in the field of neural networks. We apprentice Generative adversarial networks as an optimum solution for generating Image to image translation where our motive is to learn a mapping between an input image(X) and an output image(Y) using a set of predefined pairs[4]. But it is not necessary that the paired dataset is provided to for our use and hence adversarial methods comes into existence. Further, we advance a method that is able to convert and recapture an image from a domain X to another domain Y in the absence of paired datasets. Our objective is to learn a mapping function G: A —B such that the mapping is able to distinguish the images of G(A) within the distribution of B using an adversarial loss.[1] Because this mapping is high biased, we introduce an inverse mapping function F B—A and introduce a cycle consistency loss[7]. Furthermore we wish to extend our research with various domains and involve them with neural style transfer, semantic image synthesis. Our essential commitment is to show that on a wide assortment of issues, conditional GANs produce sensible outcomes. This paper hence calls for the attention to the purpose of converting image X to image Y and we commit to the transfer learning of training dataset and optimising our code.You can find the source code for the same here.

scholarly journals Tag Disentangled Generative Adversarial Network for Object Image Re-rendering

2017 ◽  
Author(s):  
Chaoyue Wang ◽  
Chaohui Wang ◽  
Chang Xu ◽  
Dacheng Tao
Keyword(s):  
Input Image ◽  
Generative Adversarial Networks ◽  
Single Image ◽  
Generative Adversarial Network ◽  
Training Strategy ◽  
Adversarial Network ◽  
Adversarial Networks ◽  
Adversarial Training ◽  
Realistic Images

In this paper, we propose a principled Tag Disentangled Generative Adversarial Networks (TD-GAN) for re-rendering new images for the object of interest from a single image of it by specifying multiple scene properties (such as viewpoint, illumination, expression, etc.). The whole framework consists of a disentangling network, a generative network, a tag mapping net, and a discriminative network, which are trained jointly based on a given set of images that are completely/partially tagged (i.e., supervised/semi-supervised setting). Given an input image, the disentangling network extracts disentangled and interpretable representations, which are then used to generate images by the generative network. In order to boost the quality of disentangled representations, the tag mapping net is integrated to explore the consistency between the image and its tags. Furthermore, the discriminative network is introduced to implement the adversarial training strategy for generating more realistic images. Experiments on two challenging datasets demonstrate the state-of-the-art performance of the proposed framework in the problem of interest.

scholarly journals Understanding Trending Variants of Generative Adversarial Networks

2018 ◽  
Vol 7 (3.12) ◽  
pp. 864
Author(s):  
Tanvi Bhandarkar ◽  
A Murugan
Keyword(s):  
Intelligent Systems ◽  
Applied Field ◽  
Domain Adaptation ◽  
Generative Adversarial Networks ◽  
High Dimensional ◽  
Adversarial Networks ◽  
Academic Fields ◽  
Image Translation ◽  
Latent Space ◽  
Adversarial Models

Generative Adversarial Networks (GAN) have its major contribution to the field of Artificial Intelligence. It is becoming so powerful by paving its way in numerous applications of intelligent systems. This is primarily due to its astute prospect of learning and solving complex and high-dimensional problems from the latent space. With the growing demands of GANs, it is necessary to seek its potential and impact in implementations. In short span of time, it has witnessed several variants and extensions in image translation, domain-adaptation and other academic fields. This paper provides an understanding of such imperative GANs mutants and surveys the existing adversarial models which are prominent in their applied field. 

scholarly journals Generative Reversible Data Hiding by Image-to-Image Translation via GANs

2019 ◽  
Vol 2019 ◽  
pp. 1-10 ◽  
Author(s):  
Zhuo Zhang ◽  
Guangyuan Fu ◽  
Fuqiang Di ◽  
Changlong Li ◽  
Jia Liu
Keyword(s):  
Data Hiding ◽  
Reversible Data Hiding ◽  
Input Image ◽  
Generative Adversarial Networks ◽  
Secret Message ◽  
Stego Image ◽  
Adversarial Networks ◽  
Image Translation ◽  
Realistic Image ◽  
Image Generator

The traditional reversible data hiding technique is based on cover image modification which inevitably leaves some traces of rewriting that can be more easily analyzed and attacked by the warder. Inspired by the cover synthesis steganography-based generative adversarial networks, in this paper, a novel generative reversible data hiding (GRDH) scheme by image translation is proposed. First, an image generator is used to obtain a realistic image, which is used as an input to the image-to-image translation model with CycleGAN. After image translation, a stego image with different semantic information will be obtained. The secret message and the original input image can be recovered separately by a well-trained message extractor and the inverse transform of the image translation. The experimental results have verified the effectiveness of the scheme.

scholarly journals SliderGAN: Synthesizing Expressive Face Images by Sliding 3D Blendshape Parameters

2020 ◽  
Vol 128 (10-11) ◽  
pp. 2629-2650
Author(s):  
Evangelos Ververas ◽  
Stefanos Zafeiriou
Keyword(s):  
Input Image ◽  
Generative Adversarial Networks ◽  
Deep Convolutional Neural Networks ◽  
Regression Problem ◽  
Facial Motion ◽  
Adversarial Networks ◽  
Face Images ◽  
Image Translation ◽  
Image Pairs ◽  
Blendshape Model

Abstract Image-to-image (i2i) translation is the dense regression problem of learning how to transform an input image into an output using aligned image pairs. Remarkable progress has been made in i2i translation with the advent of deep convolutional neural networks and particular using the learning paradigm of generative adversarial networks (GANs). In the absence of paired images, i2i translation is tackled with one or multiple domain transformations (i.e., CycleGAN, StarGAN etc.). In this paper, we study the problem of image-to-image translation, under a set of continuous parameters that correspond to a model describing a physical process. In particular, we propose the SliderGAN which transforms an input face image into a new one according to the continuous values of a statistical blendshape model of facial motion. We show that it is possible to edit a facial image according to expression and speech blendshapes, using sliders that control the continuous values of the blendshape model. This provides much more flexibility in various tasks, including but not limited to face editing, expression transfer and face neutralisation, comparing to models based on discrete expressions or action units.

Sign in / Sign up

Export Citation Format

Share Document