Related papers: Separate Universe Super-Resolution Emulator

Using the N-body simulations of the AEMULUS Project, we construct an emulator for the non-linear clustering of galaxies in real and redshift space. We construct our model of galaxy bias using the halo occupation framework, accounting for…

Novel architectures have recently improved generative image synthesis leading to excellent visual quality in various tasks. Much of this success is due to the scalability of these architectures and hence caused by a dramatic increase in…

Despite the breakthroughs in accuracy and speed of single image super-resolution using faster and deeper convolutional neural networks, one central problem remains largely unsolved: how do we recover the finer texture details when we…

Super-resolution is an innovative technique that upscales the resolution of an image or a video and thus enables us to reconstruct high-fidelity images from low-resolution data. This study performs super-resolution analysis on turbulent…

Mesh-based simulations provide high-fidelity solutions to partial differential equations (PDEs), but achieving such accuracy typically requires fine meshes, leading to substantial computational overhead. Super-resolution techniques aim to…

We propose a one-shot ultra-high-resolution generative adversarial network (OUR-GAN) framework that generates non-repetitive 16K (16, 384 x 8, 640) images from a single training image and is trainable on a single consumer GPU. OUR-GAN…

Superpixels provide a compact region-based representation that preserves object boundaries and local structures, and have therefore been widely used in a variety of vision tasks to reduce computational cost. However, most existing…

In this paper, we explore the use of a variational autoencoder (VAE), a deep generative model, to compress and generate images of dark matter density fields from $\Lambda$CDM like cosmological simulations. The VAE learns a compact,…

The gravitationally-driven evolution of cold dark matter dominates the formation of structure in the Universe over a wide range of length scales. While the longest scales can be treated by perturbation theory, a fully quantitative…

An ongoing trend in generative modelling research has been to push sample resolutions higher whilst simultaneously reducing computational requirements for training and sampling. We aim to push this trend further via the combination of…

The determination of the resolution of cosmological N-body simulations, i.e., the range of scales in which quantities measured in them represent accurately the continuum limit, is an important open question. We address it here using…

We examine the effects of mass resolution and force softening on the density profiles of cold dark matter halos that form within cosmological N-body simulations. As we increase the mass and force resolution, we resolve progenitor halos that…

This work presents a deep learning surrogate model for the fast simulation of high-dimensional frequency selective surfaces. We consider unit-cells which are built as multiple concatenated stacks of screens and their design requires the…

Deep learning-based super-resolution models have the potential to revolutionize biomedical imaging and diagnoses by effectively tackling various challenges associated with early detection, personalized medicine, and clinical automation.…

This work presents a novel physics-informed deep learning based super-resolution framework to reconstruct high-resolution deformation fields from low-resolution counterparts, obtained from coarse mesh simulations or experiments. We leverage…

Single-image super-resolution is a fundamental task for vision applications to enhance the image quality with respect to spatial resolution. If the input image contains degraded pixels, the artifacts caused by the degradation could be…

Chemo-dynamical N-body simulations are an essential tool for understanding the formation and evolution of galaxies. As the number of observationally determined stellar abundances continues to climb, these simulations are able to provide new…

We present a method to construct semi-numerical ``simulations'', which can efficiently generate realizations of halo distributions and ionization maps at high redshifts. Our procedure combines an excursion-set approach with first-order…

A recurring challenge in self-supervised learning is preventing representation collapse. Existing solutions typically rely on global regularization, such as maximizing distances, decorrelating dimensions or enforcing certain distributions.…

Generative deep learning architectures can produce realistic, high-resolution fake imagery -- with potentially drastic societal implications. A key question in this context is: How easy is it to generate realistic imagery, in particular for…