scholarly journals Deblending galaxy superpositions with branched generative adversarial networks

2019 ◽  
Vol 485 (2) ◽  
pp. 2617-2627 ◽  
Author(s):  
David M Reiman ◽  
Brett E Göhre
Keyword(s):  
Signal To Noise Ratio ◽  
Ground Truth ◽  
Structural Similarity ◽  
Generative Models ◽  
Generative Adversarial Networks ◽  
Wide Field ◽  
Generative Adversarial Network ◽  
Galaxy Surveys ◽  
Adversarial Network ◽  
Natural Choice

Abstract Near-future large galaxy surveys will encounter blended galaxy images at a fraction of up to 50 per cent in the densest regions of the Universe. Current deblending techniques may segment the foreground galaxy while leaving missing pixel intensities in the background galaxy flux. The problem is compounded by the diffuse nature of galaxies in their outer regions, making segmentation significantly more difficult than in traditional object segmentation applications. We propose a novel branched generative adversarial network to deblend overlapping galaxies, where the two branches produce images of the two deblended galaxies. We show that generative models are a powerful engine for deblending given their innate ability to infill missing pixel values occluded by the superposition. We maintain high peak signal-to-noise ratio and structural similarity scores with respect to ground truth images upon deblending. Our model also predicts near-instantaneously, making it a natural choice for the immense quantities of data soon to be created by large surveys such as Large Synoptic Survey Telescope, Euclid, and Wide-Field Infrared Survey Telescope.

scholarly journals Application of a Modified Generative Adversarial Network in the Superresolution Reconstruction of Ancient Murals

2020 ◽  
Vol 2020 ◽  
pp. 1-12
Author(s):  
Jianfang Cao ◽  
Zibang Zhang ◽  
Aidi Zhao
Keyword(s):  
High Resolution ◽  
Signal To Noise Ratio ◽  
Reconstruction Algorithm ◽  
Structural Similarity ◽  
Image Feature ◽  
Generative Adversarial Network ◽  
Resolution Image ◽  
High Resolution Image ◽  
Adversarial Network ◽  
Set Up

Considering the problems of low resolution and rough details in existing mural images, this paper proposes a superresolution reconstruction algorithm for enhancing artistic mural images, thereby optimizing mural images. The algorithm takes a generative adversarial network (GAN) as the framework. First, a convolutional neural network (CNN) is used to extract image feature information, and then, the features are mapped to the high-resolution image space of the same size as the original image. Finally, the reconstructed high-resolution image is output to complete the design of the generative network. Then, a CNN with deep and residual modules is used for image feature extraction to determine whether the output of the generative network is an authentic, high-resolution mural image. In detail, the depth of the network increases, the residual module is introduced, the batch standardization of the network convolution layer is deleted, and the subpixel convolution is used to realize upsampling. Additionally, a combination of multiple loss functions and staged construction of the network model is adopted to further optimize the mural image. A mural dataset is set up by the current team. Compared with several existing image superresolution algorithms, the peak signal-to-noise ratio (PSNR) of the proposed algorithm increases by an average of 1.2–3.3 dB and the structural similarity (SSIM) increases by 0.04 = 0.13; it is also superior to other algorithms in terms of subjective scoring. The proposed method in this study is effective in the superresolution reconstruction of mural images, which contributes to the further optimization of ancient mural images.

scholarly journals Learning Representations of Natural Language Texts with Generative Adversarial Networks at Document, Sentence, and Aspect Level

Algorithms ◽  
2018 ◽  
Vol 11 (10) ◽  
pp. 164 ◽  
Author(s):  
Aggeliki Vlachostergiou ◽  
George Caridakis ◽  
Phivos Mylonas ◽  
Andreas Stafylopatis
Keyword(s):  
Natural Language ◽  
Generative Models ◽  
Generative Adversarial Networks ◽  
Real World Data ◽  
Generative Adversarial Network ◽  
Feature Representations ◽  
Adversarial Network ◽  
Adversarial Networks ◽  
Learning Tasks ◽  
Potential Applications

The ability to learn robust, resizable feature representations from unlabeled data has potential applications in a wide variety of machine learning tasks. One way to create such representations is to train deep generative models that can learn to capture the complex distribution of real-world data. Generative adversarial network (GAN) approaches have shown impressive results in producing generative models of images, but relatively little work has been done on evaluating the performance of these methods for the learning representation of natural language, both in supervised and unsupervised settings at the document, sentence, and aspect level. Extensive research validation experiments were performed by leveraging the 20 Newsgroups corpus, the Movie Review (MR) Dataset, and the Finegrained Sentiment Dataset (FSD). Our experimental analysis suggests that GANs can successfully learn representations of natural language texts at all three aforementioned levels.

scholarly journals Improvement of Learning Stability of Generative Adversarial Network Using Variational Learning

2020 ◽  
Vol 10 (13) ◽  
pp. 4528
Author(s):  
Je-Yeol Lee ◽  
Sang-Il Choi 
Keyword(s):  
Generative Models ◽  
Learning Processes ◽  
Generative Adversarial Networks ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Adversarial Networks ◽  
Secondary Network ◽  
Variational Autoencoder ◽  
Variational Learning

In this paper, we propose a new network model using variational learning to improve the learning stability of generative adversarial networks (GAN). The proposed method can be easily applied to improve the learning stability of GAN-based models that were developed for various purposes, given that the variational autoencoder (VAE) is used as a secondary network while the basic GAN structure is maintained. When the gradient of the generator vanishes in the learning process of GAN, the proposed method receives gradient information from the decoder of the VAE that maintains gradient stably, so that the learning processes of the generator and discriminator are not halted. The experimental results of the MNIST and the CelebA datasets verify that the proposed method improves the learning stability of the networks by overcoming the vanishing gradient problem of the generator, and maintains the excellent data quality of the conventional GAN-based generative models.

scholarly journals QCBCT-NET for direct measurement of bone mineral density from quantitative cone-beam CT: a human skull phantom study

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Tae-Hoon Yong ◽  
Su Yang ◽  
Sang-Jeong Lee ◽  
Chansoo Park ◽  
Jo-Eun Kim ◽  
...  
Keyword(s):  
Signal To Noise Ratio ◽  
Cone Beam Ct ◽  
Structural Similarity ◽  
Training Data ◽  
Cone Beam ◽  
Absolute Difference ◽  
Mineral Density ◽  
Quantitative Ct ◽  
Generative Adversarial Network ◽  
Adversarial Network

AbstractThe purpose of this study was to directly and quantitatively measure BMD from Cone-beam CT (CBCT) images by enhancing the linearity and uniformity of the bone intensities based on a hybrid deep-learning model (QCBCT-NET) of combining the generative adversarial network (Cycle-GAN) and U-Net, and to compare the bone images enhanced by the QCBCT-NET with those by Cycle-GAN and U-Net. We used two phantoms of human skulls encased in acrylic, one for the training and validation datasets, and the other for the test dataset. We proposed the QCBCT-NET consisting of Cycle-GAN with residual blocks and a multi-channel U-Net using paired training data of quantitative CT (QCT) and CBCT images. The BMD images produced by QCBCT-NET significantly outperformed the images produced by the Cycle-GAN or the U-Net in mean absolute difference (MAD), peak signal to noise ratio (PSNR), normalized cross-correlation (NCC), structural similarity (SSIM), and linearity when compared to the original QCT image. The QCBCT-NET improved the contrast of the bone images by reflecting the original BMD distribution of the QCT image locally using the Cycle-GAN, and also spatial uniformity of the bone images by globally suppressing image artifacts and noise using the two-channel U-Net. The QCBCT-NET substantially enhanced the linearity, uniformity, and contrast as well as the anatomical and quantitative accuracy of the bone images, and demonstrated more accuracy than the Cycle-GAN and the U-Net for quantitatively measuring BMD in CBCT.

scholarly journals Human Face Generation using Deep Convolution Generative Adversarial Network

2021 ◽  
Vol 7 (01) ◽  
pp. 114-120
Author(s):  
Chaudhary Sarimurrab, Ankita Kesari Naman and Sudha Narang
Keyword(s):  
Random Noise ◽  
Generative Models ◽  
Generative Adversarial Networks ◽  
Data Generation ◽  
Generative Adversarial Network ◽  
Practical Applications ◽  
Adversarial Network ◽  
Adversarial Networks ◽  
Face Generation ◽  
Human Faces

The Generative Models have gained considerable attention in the field of unsupervised learning via a new and practical framework called Generative Adversarial Networks (GAN) due to its outstanding data generation capability. Many models of GAN have proposed, and several practical applications emerged in various domains of computer vision and machine learning. Despite GAN's excellent success, there are still obstacles to stable training. In this model, we aim to generate human faces through un-labelled data via the help of Deep Convolutional Generative Adversarial Networks. The applications for generating faces are vast in the field of image processing, entertainment, and other such industries. Our resulting model is successfully able to generate human faces from the given un-labelled data and random noise.

scholarly journals iSeeBetter: Spatio-temporal video super-resolution using recurrent generative back-projection networks

2020 ◽  
Vol 6 (3) ◽  
pp. 307-317
Author(s):  
Aman Chadha ◽  
John Britto ◽  
M. Mani Roja
Keyword(s):  
Mean Squared Error ◽  
Signal To Noise Ratio ◽  
Super Resolution ◽  
Structural Similarity ◽  
Generative Adversarial Networks ◽  
Video Frame ◽  
Perceptual Quality ◽  
Back Projection ◽  
Generative Adversarial Network ◽  
Spatio Temporal

Abstract Recently, learning-based models have enhanced the performance of single-image super-resolution (SISR). However, applying SISR successively to each video frame leads to a lack of temporal coherency. Convolutional neural networks (CNNs) outperform traditional approaches in terms of image quality metrics such as peak signal to noise ratio (PSNR) and structural similarity (SSIM). On the other hand, generative adversarial networks (GANs) offer a competitive advantage by being able to mitigate the issue of a lack of finer texture details, usually seen with CNNs when super-resolving at large upscaling factors. We present iSeeBetter, a novel GAN-based spatio-temporal approach to video super-resolution (VSR) that renders temporally consistent super-resolution videos. iSeeBetter extracts spatial and temporal information from the current and neighboring frames using the concept of recurrent back-projection networks as its generator. Furthermore, to improve the “naturality” of the super-resolved output while eliminating artifacts seen with traditional algorithms, we utilize the discriminator from super-resolution generative adversarial network. Although mean squared error (MSE) as a primary loss-minimization objective improves PSNR/SSIM, these metrics may not capture fine details in the image resulting in misrepresentation of perceptual quality. To address this, we use a four-fold (MSE, perceptual, adversarial, and total-variation loss function. Our results demonstrate that iSeeBetter offers superior VSR fidelity and surpasses state-of-the-art performance.

Colorization of fusion image of infrared and visible images based on parallel generative adversarial network approach

2021 ◽  
pp. 1-10
Author(s):  
Lei Chen ◽  
Jun Han ◽  
Feng Tian
Keyword(s):  
Ground Truth ◽  
Objective Evaluation ◽  
Generative Adversarial Networks ◽  
Data Sets ◽  
Fusion Image ◽  
Generative Adversarial Network ◽  
Visible Image ◽  
Low Contrast ◽  
Adversarial Network ◽  
Visible Images

Fusing the infrared (IR) and visible images has many advantages and can be applied to applications such as target detection and recognition. Colors can give more accurate and distinct features, but the low resolution and low contrast of fused images make this a challenge task. In this paper, we proposed a method based on parallel generative adversarial networks (GANs) to address the challenge. We used IR image, visible image and fusion image as ground truth of ‘L’, ‘a’ and ‘b’ of the Lab model. Through the parallel GANs, we can gain the Lab data which can be converted to RGB image. We adopt TNO and RoadScene data sets to verify our method, and compare with five objective evaluation parameters obtained by other three methods based on deep learning (DL). It is demonstrated that the proposed approach is able to achieve better performance against state-of-arts methods.

scholarly journals GENERATIVE ADVERSARIAL NETWORKS AS A NOVEL APPROACH FOR TECTONIC FAULT AND FRACTURE EXTRACTION IN HIGH-RESOLUTION SATELLITE AND AIRBORNE OPTICAL IMAGES

2020 ◽  
Vol XLIII-B3-2020 ◽  
pp. 1219-1227
Author(s):  
B. Jafrasteh ◽  
I. Manighetti ◽  
J. Zerubia
Keyword(s):  
Ground Truth ◽  
Generative Adversarial Networks ◽  
Generative Adversarial Network ◽  
Convolutional Networks ◽  
Adversarial Network ◽  
Adversarial Networks ◽  
Optical Images ◽  
Novel Approach ◽  
Ground Truth Image ◽  
Novel Method

Abstract. We develop a novel method based on Deep Convolutional Networks (DCN) to automate the identification and mapping of fracture and fault traces in optical images. The method employs two DCNs in a two players game: a first network, called Generator, learns to segment images to make them resembling the ground truth; a second network, called Discriminator, measures the differences between the ground truth image and each segmented image and sends its score feedback to the Generator; based on these scores, the Generator improves its segmentation progressively. As we condition both networks to the ground truth images, the method is called Conditional Generative Adversarial Network (CGAN). We propose a new loss function for both the Generator and the Discriminator networks, to improve their accuracy. Using two criteria and a manually annotated optical image, we compare the generalization performance of the proposed method to that of a classical DCN architecture, U-net. The comparison demonstrates the suitability of the proposed CGAN architecture. Further work is however needed to improve its efficiency.

scholarly journals An Image Denoising Method Based on BM4D and GAN in 3D Shearlet Domain

2020 ◽  
Vol 2020 ◽  
pp. 1-11
Author(s):  
Shengnan Zhang ◽  
Lei Wang ◽  
Chunhong Chang ◽  
Cong Liu ◽  
Longbo Zhang ◽  
...  
Keyword(s):  
Image Denoising ◽  
Signal To Noise Ratio ◽  
Evaluation Criteria ◽  
Structural Similarity ◽  
Block Matching ◽  
Generative Adversarial Network ◽  
Denoising Method ◽  
Edge Preserving ◽  
Block Matching Algorithm ◽  
Adversarial Network

To overcome the disadvantages of the traditional block-matching-based image denoising method, an image denoising method based on block matching with 4D filtering (BM4D) in the 3D shearlet transform domain and a generative adversarial network is proposed. Firstly, the contaminated images are decomposed to get the shearlet coefficients; then, an improved 3D block-matching algorithm is proposed in the hard threshold and wiener filtering stage to get the latent clean images; the final clean images can be obtained by training the latent clean images via a generative adversarial network (GAN).Taking the peak signal-to-noise ratio (PSNR), structural similarity (SSIM for short) of image, and edge-preserving index (EPI for short) as the evaluation criteria, experimental results demonstrate that the proposed method can not only effectively remove image noise in high noisy environment, but also effectively improve the visual effect of the images.

Synthesizing Designs With Inter-Part Dependencies Using Hierarchical Generative Adversarial Networks

2018 ◽  
Author(s):  
Wei Chen ◽  
Ashwin Jeyaseelan ◽  
Mark Fuge
Keyword(s):  
Real World ◽  
Generative Models ◽  
Generative Adversarial Networks ◽  
Generative Adversarial Network ◽  
Design Exploration ◽  
Adversarial Network ◽  
Adversarial Networks ◽  
Latent Space ◽  
Latent Representations

Real-world designs usually consist of parts with hierarchical dependencies, i.e., the geometry of one component (a child shape) is dependent on another (a parent shape). We propose a method for synthesizing this type of design. It decomposes the problem of synthesizing the whole design into synthesizing each component separately but keeping the inter-component dependencies satisfied. This method constructs a two-level generative adversarial network to train two generative models for parent and child shapes, respectively. We then use the trained generative models to synthesize or explore parent and child shapes separately via a parent latent representation and infinite child latent representations, each conditioned on a parent shape. We evaluate and discuss the disentanglement and consistency of latent representations obtained by this method. We show that shapes change consistently along any direction in the latent space. This property is desirable for design exploration over the latent space.

Sign in / Sign up

Export Citation Format

Share Document