Related papers: BCDDM: Branch-Corrected Denoising Diffusion Model …
Denoising diffusion probabilistic models (DDPMs) have achieved impressive performance on various image generation tasks, including image super-resolution. By learning to reverse the process of gradually diffusing the data distribution into…
Finding corresponding pixels within a pair of images is a fundamental computer vision task with various applications. Due to the specific requirements of different tasks like optical flow estimation and local feature matching, previous…
Diffusion and flow matching models have achieved remarkable success in text-to-image generation. However, these models typically rely on the predetermined denoising schedules for all prompts. The multi-step reverse diffusion process can be…
Denoising diffusion probabilistic models (DDPMs) have emerged as competitive generative models yet brought challenges to efficient sampling. In this paper, we propose novel bilateral denoising diffusion models (BDDMs), which take…
Although many long-range imaging systems are designed to support extended vision applications, a natural obstacle to their operation is degradation due to atmospheric turbulence. Atmospheric turbulence causes significant degradation to…
The denoising process of diffusion models can be interpreted as an approximate projection of noisy samples onto the data manifold. Moreover, the noise level in these samples approximates their distance to the underlying manifold. Building…
Low-dose computed tomography (CT) images suffer from noise and artifacts due to photon starvation and electronic noise. Recently, some works have attempted to use diffusion models to address the over-smoothness and training instability…
Accreting massive black holes (MBHs, with M$_\bullet > 10^3$ M$_{\odot}$) are known for their panchromatic emission, spanning from radio to gamma rays. While MBHs accreting at significant fractions of their Eddington rate are readily…
X-ray binaries (XRBs) display spectral state transitions that are accompanied by substantial changes in the hardness, luminosity, and structure of the accretion flow. We developed a GPU-accelerated cooling toolkit for general relativistic…
We run three long-timescale general-relativistic magnetohydrodynamic simulations of radiatively inefficient accretion flows onto non-rotating black holes. Our aim is to achieve steady-state behavior out to large radii and understand the…
Discovery of high-redshift (z > 6) supermassive black holes (BHs) may indicate that the rapid (or super-Eddington) gas accretion has aided their quick growth. Here, we study such rapid accretion of the primordial gas on to intermediate-mass…
The Event Horizon Telescope (EHT) has produced images of two supermassive black holes, Messier~87* (M 87*) and Sagittarius~A* (Sgr A*). The EHT collaboration used these images to indirectly constrain black hole parameters by calibrating…
Diffusion models (DM) have achieved remarkable promise in image super-resolution (SR). However, most of them are tailored to solving non-blind inverse problems with fixed known degradation settings, limiting their adaptability to real-world…
We perform three general-relativistic magnetohydrodynamic simulations of black hole accretion designed to test how sensitive results are to grid resolution in the jet region. The cases differ only in numerics, modelling the same physical…
General Relativistic Magnetohydrodynamics (GRMHD) simulations are an indispensable tool in studying accretion onto compact objects. The Event Horizon Telescope (EHT) frequently uses libraries of ideal GRMHD simulations to interpret…
Diffusion models (DMs) are capable of generating remarkably high-quality samples by iteratively denoising a random vector, a process that corresponds to moving along the probability flow ordinary differential equation (PF ODE).…
In this note, we develop a prescription for describing BPS black hole microstates in terms of a holographic conformal quantum mechanics (CQM) model dual to the near-horizon $AdS_2$ geometry of the black hole. We use 1/2 BPS small black…
We investigate the utility of diffusion generative models to efficiently synthesise datasets that effectively train deep learning models for image analysis. Specifically, we propose novel $\Gamma$-distribution Latent Denoising Diffusion…
This work introduces InJecteD, a framework for interpreting Denoising Diffusion Probabilistic Models (DDPMs) by analyzing sample trajectories during the denoising process of 2D point cloud generation. We apply this framework to three…
We present a novel generative approach based on Denoising Diffusion Models (DDMs), which produces high-quality image samples along with their losslessly compressed bit-stream representations. This is obtained by replacing the standard…