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

The massive exploitation of cosmic voids for precision cosmology in the upcoming dark energy experiments, requires a robust understanding of their internal structure, particularly of their density profile. We show that the void density…

Generative Adversarial Networks (GANs) are very popular frameworks for generating high-quality data, and are immensely used in both the academia and industry in many domains. Arguably, their most substantial impact has been in the area of…

Generative adversarial networks (GANs) have been extensively studied in the past few years. Arguably their most significant impact has been in the area of computer vision where great advances have been made in challenges such as plausible…

We study how the properties of cosmic voids depend on those of the tracer galaxy populations in which they are identified. We use a suite of halo occupation distribution (HOD) mocks in a simulation, identify voids in these populations using…

Generative adversarial networks (GANs) are unsupervised Deep Learning approach in the computer vision community which has gained significant attention from the last few years in identifying the internal structure of multimodal medical…

We study the formation and evolution of voids in the dark matter distribution using various simulations of the popular $\Lambda$ Cold Dark Matter cosmogony. We identify voids by requiring them to be regions of space with a mean overdensity…

In this paper, we propose a novel application of Generative Adversarial Networks (GAN) to the synthesis of cells imaged by fluorescence microscopy. Compared to natural images, cells tend to have a simpler and more geometric global structure…

Deep generative models learned through adversarial training have become increasingly popular for their ability to generate naturalistic image textures. However, aside from their texture, the visual appearance of objects is significantly…

Cosmic voids may have novel affects on the propagation of high-energy photons. We consider the fraction of the line of sight that intersect voids (termed \enquote{voidiness}). A previous study showed that active galactic nuclei (AGN)…

We present a study of spectral properties of galaxies in underdense large-scale structures, voids. Our void galaxy sample (75,939 galaxies) is selected from the Sloan Digital Sky Survey (SDSS) Data Release 7 (DR7) with $\rm z < 0.107$. We…

One of the biggest challenges in the research of generative adversarial networks (GANs) is assessing the quality of generated samples and detecting various levels of mode collapse. In this work, we construct a novel measure of performance…

Generative Adversarial Networks (GANs) have obtained extraordinary success in the generation of realistic images, a domain where a lower pixel-level accuracy is acceptable. We study the problem, not yet tackled in the literature, of…

Generative adversarial networks (GANs) have demonstrated to be successful at generating realistic real-world images. In this paper we compare various GAN techniques, both supervised and unsupervised. The effects on training stability of…

In the past several decades, many attempts have been made to model synthetic realistic geometric data. The goal of such models is to generate plausible 3D geometries and textures. Perhaps the best known of its kind is the linear 3D…

In recent years, Generative Adversarial Networks (GANs) have shown substantial progress in modeling complex distributions of data. These networks have received tremendous attention since they can generate implicit probabilistic models that…

A promise of Generative Adversarial Networks (GANs) is to provide cheap photorealistic data for training and validating AI models in autonomous driving. Despite their huge success, their performance on complex images featuring multiple…

Cosmic voids are underdense regions within the large-scale structure of the Universe, spanning a wide range of physical scales - from a few megaparsecs (Mpc) to the largest observable structures. Their distinctive properties make them…

Generative Adversarial Networks (GANs) produce high-quality images but are challenging to train. They need careful regularization, vast amounts of compute, and expensive hyper-parameter sweeps. We make significant headway on these issues by…

Generative adversarial networks (GANs) are a class of unsupervised machine learning algorithms that can produce realistic images from randomly-sampled vectors in a multi-dimensional space. Until recently, it was not possible to generate…

Recently, Generative Adversarial Networks (GANs) trained on samples of traditionally simulated collider events have been proposed as a way of generating larger simulated datasets at a reduced computational cost. In this paper we point out…