Related papers: Can denoising diffusion probabilistic models gener…
In recent years, diffusion models (DMs) have become a popular method for generating synthetic data. By achieving samples of higher quality, they quickly became superior to generative adversarial networks (GANs) and the current…
Diffusion models (DMs) are a type of generative model that has a huge impact on image synthesis and beyond. They achieve state-of-the-art generation results in various generative tasks. A great diversity of conditioning inputs, such as text…
We introduce the state-of-the-art deep learning Denoising Diffusion Probabilistic Model (DDPM) as a method to infer the volume or number density of giant molecular clouds (GMCs) from projected mass surface density maps. We adopt…
We propose a new description of astronomical dust emission in the spectral region from the Far-Infrared to millimeter wavelengths. Unlike previous classical models, this description explicitly incorporates the effect of the disordered…
The construction of viable and physically-realistic interstellar dust models is only possible if the constraints imposed by laboratory data on interstellar dust analogue materials are respected and used within a meaningful theoretical…
Following from our recent work, we present results of a detailed analysis of a representative sample of nearby galaxies. The photometric parameters of the morphological components are obtained from bulge-disk decompositions, using GALFIT…
Diffusion models have gained attention for their ability to represent complex distributions and incorporate uncertainty, making them ideal for robust predictions in the presence of noisy or incomplete data. In this study, we develop and…
Implicit models, which allow for the generation of samples but not for point-wise evaluation of probabilities, are omnipresent in real-world problems tackled by machine learning and a hot topic of current research. Some examples include…
Generative models are a promising tool to produce cosmological simulations but face significant challenges in scalability, physical consistency, and adherence to domain symmetries, limiting their utility as alternatives to $N$-body…
Nanometer- and micrometer-sized solid particles play an important role in the evolutionary cycle of stars and interstellar matter. The optical properties of cosmic grains determine the interaction of the radiation field with the solids,…
Diffusion-based generative models represent the current state-of-the-art for image generation. However, standard diffusion models are based on Euclidean geometry and do not translate directly to manifold-valued data. In this work, we…
Cosmological galaxy formation simulations are still limited by their spatial/mass resolution and cannot model from first principles some of the processes, like star formation, that are key in driving galaxy evolution. As a consequence they…
Denoising diffusion probabilistic models (DDPMs) have achieved high quality image generation without adversarial training, yet they require simulating a Markov chain for many steps to produce a sample. To accelerate sampling, we present…
High Dynamic Range (HDR) images can be recovered from several Low Dynamic Range (LDR) images by existing Deep Neural Networks (DNNs) techniques. Despite the remarkable progress, DNN-based methods still generate ghosting artifacts when LDR…
Understanding the nature of dark matter in the Universe is an important goal of modern cosmology. A key method for probing this distribution is via weak gravitational lensing mass-mapping - a challenging ill-posed inverse problem where one…
Generative Adversarial Networks (GANs) have shown immense potential in fields such as text and image generation. Only very recently attempts to exploit GANs to statistical-mechanics models have been reported. Here we quantitatively test…
The simulation of geological facies in an unobservable volume is essential in various geoscience applications. Given the complexity of the problem, deep generative learning is a promising approach to overcome the limitations of traditional…
We introduce a deep generative framework for high-dimensional Bayesian inference that enables efficient posterior sampling. As telescopes and simulations rapidly expand the volume and resolution of astrophysical data, fast simulation-based…
Face anti-spoofing is crucial for ensuring the security and reliability of face recognition systems. Several existing face anti-spoofing methods utilize GAN-like networks to detect presentation attacks by estimating the noise pattern of a…
In radio astronomy, signals from radio telescopes are transformed into images of observed celestial objects, or sources. However, these images, called dirty images, contain real sources as well as artifacts due to signal sparsity and other…