Related papers: Cosmic Voids in GAN-Generated Maps of Large-Scale …

Unsupervised generation of high-quality multi-view-consistent images and 3D shapes using only collections of single-view 2D photographs has been a long-standing challenge. Existing 3D GANs are either compute-intensive or make approximations…

This paper investigates conditional generative adversarial networks (cGANs) to overcome a fundamental limitation of using geotagged media for geographic discovery, namely its sparse and uneven spatial distribution. We train a cGAN to…

Observations of astrophysical objects such as galaxies are limited by various sources of random and systematic noise from the sky background, the optical system of the telescope and the detector used to record the data. Conventional…

The Universe is mostly composed of large and relatively empty domains known as cosmic voids, whereas its matter content is predominantly distributed along their boundaries. The remaining material inside them, either dark or luminous matter,…

Generative adversarial network (GAN) is widely used for generalized and robust learning on graph data. However, for non-Euclidean graph data, the existing GAN-based graph representation methods generate negative samples by random walk or…

Several research groups have shown that Generative Adversarial Networks (GANs) can generate photo-realistic images in recent years. Using the GANs, a map is created between a latent code and a photo-realistic image. This process can also be…

The properties of large underdensities in the distribution of galaxies in the Universe, known as cosmic voids, are potentially sensitive probes of fundamental physics. We use data from the MultiDark suite of N-body simulations and multiple…

Generative Adversarial Networks (GANs) are increasingly used to generate synthetic medical images, addressing the critical shortage of annotated data for training Artificial Intelligence systems. This study introduces CRF-GAN, a novel…

Neural samplers such as variational autoencoders (VAEs) or generative adversarial networks (GANs) approximate distributions by transforming samples from a simple random source---the latent space---to samples from a more complex distribution…

We address the problem of generating images across two drastically different views, namely ground (street) and aerial (overhead) views. Image synthesis by itself is a very challenging computer vision task and is even more so when generation…

Generative adversarial networks (GANs) were initially proposed to generate images by learning from a large number of samples. Recently, GANs have been used to emulate complex physical systems such as turbulent flows. However, a critical…

Automatic colorization of images without human intervention has been a subject of interest in the machine learning community for a brief period of time. Assigning color to an image is a highly ill-posed problem because of its innate nature…

Despite remarkable performance in producing realistic samples, Generative Adversarial Networks (GANs) often produce low-quality samples near low-density regions of the data manifold, e.g., samples of minor groups. Many techniques have been…

For the 2dFGRS we study the properties of voids and of fainter galaxies within voids that are defined by brighter galaxies. Our results are compared with simulated galaxy catalogues from the Millenium simulation coupled with a…

A longstanding problem in machine learning is to find unsupervised methods that can learn the statistical structure of high dimensional signals. In recent years, GANs have gained much attention as a possible solution to the problem, and in…

Using a large-scale, experimentally captured 3D microstructure dataset, we implement the generative adversarial network (GAN) framework to learn and generate 3D microstructures of solid oxide fuel cell electrodes. The generated…

In recent years, Generative Adversarial Networks (GANs) have received significant attention from the research community. With a straightforward implementation and outstanding results, GANs have been used for numerous applications. Despite…

Generative Adversarial Networks (GANs) is a powerful family of models that learn an underlying distribution to generate synthetic data. Many existing studies of GANs focus on improving the realness of the generated image data for visual…

We study the formation of voids in a modified gravity model in which gravity is generically stronger or weaker on large scales. We show that void abundances provide complementary information to halo abundances: if normalized to the CMB,…

Generative adversarial networks are a promising tool for image generation in the astronomy domain. Of particular interest are conditional generative adversarial networks (cGANs), which allow you to divide images into several classes…