Related papers: Accelerating Black Hole Image Generation via Laten…
The properties of black holes and accretion flows can be inferred by fitting Event Horizon Telescope (EHT) data to simulated images generated through general relativistic ray tracing (GRRT). However, due to the computationally intensive…
Images of black holes encode both astrophysical and gravitational properties. Detecting highly-lensed features in images can differentiate between these two effects. We present an accretion disk emission model coupled to the Adaptive…
By decomposing the image formation process into a sequential application of denoising autoencoders, diffusion models (DMs) achieve state-of-the-art synthesis results on image data and beyond. Additionally, their formulation allows for a…
In anticipation of future multi-frequency observations of black hole with the Next Generation Event Horizon Telescope (ngEHT), we construct spectral images of a thin accretion disk around a spherically symmetric black hole immersed in cold,…
High-precision regression of physical parameters from black hole images generated by General Relativistic Ray Tracing (GRRT) is essential for investigating spacetime curvature and advancing black hole astrophysics. However, due to…
Diffusion models are emerging as powerful solutions for generating high-fidelity and diverse images, often surpassing GANs under many circumstances. However, their slow inference speed hinders their potential for real-time applications. To…
Recently, diffusion models have shown remarkable results in image synthesis by gradually removing noise and amplifying signals. Although the simple generative process surprisingly works well, is this the best way to generate image data? For…
The images of supermassive black holes surrounded by optically-thin, radiatively-inefficient accretion flows, like those observed with the Event Horizon Telescope, are characterized by a bright ring of emission surrounding the black-hole…
The recent use of diffusion prior, enhanced by pre-trained text-image models, has markedly elevated the performance of image super-resolution (SR). To alleviate the huge computational cost required by pixel-based diffusion SR, latent-based…
Flood prediction is critical for emergency planning and response to mitigate human and economic losses. Traditional physics-based hydrodynamic models generate high-resolution flood maps using numerical methods requiring fine-grid…
Geological parameterization entails the representation of a geomodel using a small set of latent variables and a mapping from these variables to grid-block properties such as porosity and permeability. Parameterization is useful for data…
The horizon-scale images of black holes obtained with the Event Horizon Telescope have provided new probes of their metrics and tests of General Relativity. The images are characterized by a bright, near circular ring from the…
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…
Latent diffusion models (LDMs) dominate high-quality image generation, yet integrating representation learning with generative modeling remains a challenge. We introduce a novel generative image modeling framework that seamlessly bridges…
In this paper, we propose LSRNA, a novel framework for higher-resolution (exceeding 1K) image generation using diffusion models by leveraging super-resolution directly in the latent space. Existing diffusion models struggle with scaling…
Image completion techniques have made significant progress in filling missing regions (i.e., holes) in images. However, large-hole completion remains challenging due to limited structural information. In this paper, we address this problem…
Diffusion models have achieved promising results in image restoration tasks, yet suffer from time-consuming, excessive computational resource consumption, and unstable restoration. To address these issues, we propose a robust and efficient…
How do diffusion generative models convert pure noise into meaningful images? In a variety of pretrained diffusion models (including conditional latent space models like Stable Diffusion), we observe that the reverse diffusion process that…
Diffusion models have been shown to implicitly generate visual content autoregressively in the frequency domain, where low-frequency components are generated earlier in the denoising process while high-frequency details emerge only in later…
Diffusion MRI (dMRI) is an advanced imaging technique characterizing tissue microstructure and white matter structural connectivity of the human brain. The demand for high-quality dMRI data is growing, driven by the need for better…