Related papers: AI-assisted super-resolution cosmological simulati…
Generative Adversarial Networks (GANs) are powerful generative models that achieved strong results, mainly in the image domain. However, the training of GANs is not trivial, presenting some challenges tackled by different strategies.…
We study the formation of dark matter halos in the concordance LCDM model over a wide range of redshifts, from z=20 to the present. Our primary focus is the halo mass function, a key probe of cosmology. By performing a large suite of…
We study the evolution of the halo-halo correlation function and bias in four cosmological models (LCDM, OCDM, tauCDM, and SCDM) using very high-resolution N-body simulations. The high force and mass resolution allows dark matter (DM) halos…
We study the biasing relation between dark-matter halos or galaxies and the underlying mass distribution, using cosmological $N$-body simulations in which galaxies are modelled via semi-analytic recipes. The nonlinear, stochastic biasing is…
Recent advances of deep learning lead to great success of image and video super-resolution (SR) methods that are based on convolutional neural networks (CNN). For video SR, advanced algorithms have been proposed to exploit the temporal…
This work addresses the problems of semantic segmentation and image super-resolution by jointly considering the performance of both in training a Generative Adversarial Network (GAN). We propose a novel architecture and domain-specific…
Most advances in 3D Generative Adversarial Networks (3D GANs) largely depend on ray casting-based volume rendering, which incurs demanding rendering costs. One promising alternative is rasterization-based 3D Gaussian Splatting (3D-GS),…
We present a method to increase the resolution of measurements of a physical system and subsequently predict its time evolution using thermodynamics-aware neural networks. Our method uses adversarial autoencoders, which reduce the…
Recently, it has been demonstrated that deep neural networks can significantly improve the performance of single image super-resolution (SISR). Numerous studies have concentrated on raising the quantitative quality of super-resolved (SR)…
Joint image-feature generative modeling has recently emerged as an effective strategy for improving diffusion training by coupling low-level VAE latents with high-level semantic features extracted from pre-trained visual encoders. However,…
Deep generative models have demonstrated the ability to create realistic audiovisual content, sometimes driven by domains of different nature. However, smooth temporal dynamics in video generation is a challenging problem. This work focuses…
We propose a new approach to Generative Adversarial Networks (GANs) to achieve an improved performance with additional robustness to its so-called and well recognized mode collapse. We first proceed by mapping the desired data onto a…
We present a new algorithm for generating merger trees and halo catalogs which explicitly ensures consistency of halo properties (mass, position, and velocity) across timesteps. Our algorithm has demonstrated the ability to improve both the…
The evolution of the phase-space density profile in dark matter (DM) halos is investigated by means of constrained simulations, designed to control the merging history of a given DM halo. Halos evolve through a series of quiescent phases of…
Understanding the impact of neutrino masses on the evolution of Universe is a crucial aspect of modern cosmology. Due to their large free streaming lengths, neutrinos significantly influence the formation of cosmic structures at non-linear…
Understanding how galaxy populations emerge and evolve from the growth of dark matter structure is a central challenge in galaxy formation theory. Semi-analytic models (SAMs) provide an efficient framework to address this problem, but…
Real-world face super-resolution (SR) is a highly ill-posed image restoration task. The fully-cycled Cycle-GAN architecture is widely employed to achieve promising performance on face SR, but prone to produce artifacts upon challenging…
To maximize the amount of information extracted from cosmological datasets, simulations that accurately represent these observations are necessary. However, traditional simulations that evolve particles under gravity by estimating…
Single image super-resolution (SISR) is a very popular topic nowadays, which has both research value and practical value. In daily life, we crop a large image into sub-images to do super-resolution and then merge them together. Although…
We perform three-dimensional simulations of homogeneous and inhomogeneous cosmologies via the coupling of a numerical relativity code for spacetime evolution and smoothed particle hydrodynamics (SPH) code. Evolution of a flat dust and…