相关论文: BCDDM: Branch-Corrected Denoising Diffusion Model …
Diffusion-based generative models (DBGMs) perturb data to a target noise distribution and reverse this process to generate samples. The choice of noising process, or inference diffusion process, affects both likelihoods and sample quality.…
We simulate the formation of Fuzzy Dark Matter (FDM) cores in the presence of a Black Hole (BH) to explore whether BHs can serve as seeds for FDM core condensation. Our analysis is based on the core-condensation via the kinetic relaxation…
We apply image moment invariant analysis to total intensity and polarimetric images calculated from general relativistic magnetohydrodynamic simulations of accreting black holes. We characterize different properties of the models in our…
Diffusion models have gained significant popularity in the field of image-to-image translation. Previous efforts applying diffusion models to image super-resolution (SR) have demonstrated that iteratively refining pure Gaussian noise using…
We propose an effective denoising diffusion model for generating high-resolution images (e.g., 1024$\times$512), trained on small-size image patches (e.g., 64$\times$64). We name our algorithm Patch-DM, in which a new feature collage…
Most real-world networks are noisy and incomplete samples from an unknown target distribution. Refining them by correcting corruptions or inferring unobserved regions typically improves downstream performance. Inspired by the impressive…
The $n=1$ photon ring is an important probe of black hole (BH) properties and will be resolved by the Black Hole Explorer (BHEX) for the first time. However, extraction of black hole parameters from observations of the $n=1$ subring is not…
In this research, we propose a novel denoising diffusion model based on shortest-path modeling that optimizes residual propagation to enhance both denoising efficiency and quality. Drawing on Denoising Diffusion Implicit Models (DDIM) and…
Recent advances in imaging and high-performance computing have made it possible to image the entire human brain at the cellular level. This is the basis to study the multi-scale architecture of the brain regarding its subdivision into brain…
High-redshift ($z>2$) blazars, with relativistic jets aligned toward us, probe the most powerful end of the active galactic nuclei (AGN) population. We aim at determining the black hole masses and mass accretion rates of high-$z$ blazars in…
Polarized synchrotron emission is a fundamental process in high-energy astrophysics, particularly in the environments around black holes and pulsars. Accurate modeling of this emission requires precise computation of the emission,…
Accretion is the dominant contribution to the cosmic massive black hole density in the Universe today. Yet, modelling it in cosmological simulations is challenging due to the dynamic range involved, as well as the theoretical uncertainties…
Measurements from the Event Horizon Telescope enabled the visualization of light emission around a black hole for the first time. So far, these measurements have been used to recover a 2D image under the assumption that the emission field…
We analyze, theoretically and empirically, the performance of generative diffusion models based on \emph{blind denoisers}, in which the denoiser is not given the noise amplitude in either the training or sampling processes. Assuming that…
We propose the first general framework to automatically correct different types of geometric distortion in a single input image. Our proposed method employs convolutional neural networks (CNNs) trained by using a large synthetic distortion…
A black hole (BH) travelling through a uniform, gaseous medium is described by Bondi-Hoyle-Lyttleton (BHL) accretion. If the medium is magnetized, then the black hole can produce relativistic outflows. We performed the first 3D,…
Diffusion models have demonstrated significant potential in producing high-quality images in medical image translation to aid disease diagnosis, localization, and treatment. Nevertheless, current diffusion models have limited success in…
We develop semi-empirical models of the supermassive black hole and active galactic nucleus (AGN) populations, which incorporate the black hole growth implied by the observed AGN luminosity function assuming a radiative efficiency \epsilon,…
Event skeleton generation, aiming to induce an event schema skeleton graph with abstracted event nodes and their temporal relations from a set of event instance graphs, is a critical step in the temporal complex event schema induction task.…
Recent score-based diffusion models (SBDMs) show promising results in unpaired image-to-image translation (I2I). However, existing methods, either energy-based or statistically-based, provide no explicit form of the interfered intermediate…