Related papers: BCDDM: Branch-Corrected Denoising Diffusion Model …
Currently, medical image domain translation operations show a high demand from researchers and clinicians. Amongst other capabilities, this task allows the generation of new medical images with sufficiently high image quality, making them…
Cloud removal (CR) remains a challenging task in remote sensing image processing. Although diffusion models (DM) exhibit strong generative capabilities, their direct applications to CR are suboptimal, as they generate cloudless images from…
Denoising diffusion models (DDMs) have recently attracted increasing attention by showing impressive synthesis quality. DDMs are built on a diffusion process that pushes data to the noise distribution and the models learn to denoise. In…
We describe results from a new technique for the prediction of complete, self-consistent X-ray spectra from three-dimensional General Relativistic magnetohydrodynamic (GRMHD) simulations of black hole accretion flows. Density and cooling…
Recent advances in general relativistic magnetohydrodynamic simulations have expanded and improved our understanding of the dynamics of black-hole accretion disks. However, current simulations do not capture the thermodynamics of electrons…
The integration of RGB and depth modalities significantly enhances the accuracy of segmenting complex indoor scenes, with depth data from RGB-D cameras playing a crucial role in this improvement. However, collecting an RGB-D dataset is more…
General Relativity predicts that the emission close to a black hole must be lensed by its strong gravitational field, illuminating the last photon orbit. This results in a dark circular area known as the black hole 'shadow'. The Event…
Black holes are believed to be one of the key ingredients of galaxy formation models, but it has been notoriously challenging to simulate them due to the very complex physics and large dynamical range of spatial scales involved. Here we…
With the forthcoming VLBI images of Sgr A* and M87, simulations of accretion flows onto black holes acquire a special importance to aid with the interpretation of the observations and to test the predictions of different accretion…
Black hole accretion is one of nature's most efficient energy extraction processes. When gas falls in, a significant fraction of its gravitational binding energy is either converted into radiation or flows outwards in the form of black…
Due to the three-dimensional nature of CT- or MR-scans, generative modeling of medical images is a particularly challenging task. Existing approaches mostly apply patch-wise, slice-wise, or cascaded generation techniques to fit the…
A variety of current models for gamma-ray bursts (GRBs) suggest a common engine - a black hole of several solar masses accreting matter from a disk at a rate 0.01 to 10 solar masses per second. Using a numerical model for relativistic disk…
Manipulating transparent objects presents significant challenges due to the complexities introduced by their reflection and refraction properties, which considerably hinder the accurate estimation of their 3D shapes. To address these…
Recent diffusion and flow matching models have demonstrated strong capabilities in image generation and editing by progressively removing noise through iterative sampling. While this enables flexible inversion for semantic-preserving edits,…
A prominent family of methods for learning data distributions relies on density ratio estimation (DRE), where a model is trained to $\textit{classify}$ between data samples and samples from some reference distribution. DRE-based models can…
We propose a simple, analytic dual-cone accretion model for horizon scale images of the cores of Low-Luminosity Active Galactic Nuclei (LLAGN), including those observed by the Event Horizon Telescope (EHT). Our underlying model is of…
In this paper, we present the Directly Denoising Diffusion Model (DDDM): a simple and generic approach for generating realistic images with few-step sampling, while multistep sampling is still preserved for better performance. DDDMs require…
Accreting supermassive black hole binaries are powerful multimessenger sources emitting both gravitational and EM radiation. Understanding the accretion dynamics of these systems and predicting their distinctive EM signals is crucial to…
The diffusion model has recently emerged as a potent approach in computer vision, demonstrating remarkable performances in the field of generative artificial intelligence. Capable of producing high-quality synthetic images, diffusion models…
We extend previous work on 3D black hole excision to the case of distorted black holes, with a variety of dynamic gauge conditions that are able to respond naturally to the spacetime dynamics. We show that the combination of excision and…