English
Related papers

Related papers: BCDDM: Branch-Corrected Denoising Diffusion Model …

200 papers

We demonstrate generating HDR images using the concerted action of multiple black-box, pre-trained LDR image diffusion models. Relying on a pre-trained LDR generative diffusion models is vital as, first, there is no sufficiently large HDR…

Graphics · Computer Science 2025-03-19 Mojtaba Bemana , Thomas Leimkühler , Karol Myszkowski , Hans-Peter Seidel , Tobias Ritschel

We present a full 360 degree (i.e., 4$\pi$ steradian) general-relativistic ray-tracing and radiative transfer calculations of accreting supermassive black holes. We perform state-of-the-art three-dimensional general relativistic…

High Energy Astrophysical Phenomena · Physics 2018-11-21 Jordy Davelaar , Thomas Bronzwaer , Daniel Kok , Ziri Younsi , Monika Mościbrodzka , Heino Falcke

The Event Horizon Telescope recently observed the first shadow of a black hole. Images like this can potentially be used to test or constrain theories of gravity and deepen the understanding in plasma physics at event horizon scales, which…

High Energy Astrophysical Phenomena · Physics 2020-05-28 Jeffrey van der Gucht , Jordy Davelaar , Luc Hendriks , Oliver Porth , Hector Olivares , Yosuke Mizuno , Christian M. Fromm , Heino Falcke

Person image synthesis with controllable body poses and appearances is an essential task owing to the practical needs in the context of virtual try-on, image editing and video production. However, existing methods face significant…

Computer Vision and Pattern Recognition · Computer Science 2024-12-30 Enbo Huang , Yuan Zhang , Faliang Huang , Guangyu Zhang , Yang Liu

Learning-based methods have attracted a lot of research attention and led to significant improvements in low-light image enhancement. However, most of them still suffer from two main problems: expensive computational cost in high resolution…

Computer Vision and Pattern Recognition · Computer Science 2023-10-03 Jiancheng Huang , Yifan Liu , Shifeng Chen

Denoising diffusion models have recently achieved state-of-the-art performance in many image-generation tasks. They do, however, require a large amount of computational resources. This limits their application to medical tasks, where we…

Computer Vision and Pattern Recognition · Computer Science 2024-09-13 Florentin Bieder , Julia Wolleb , Alicia Durrer , Robin Sandkühler , Philippe C. Cattin

This study aims to improve photon counting CT (PCCT) image resolution using denoising diffusion probabilistic models (DDPM). Although DDPMs have shown superior performance when applied to various computer vision tasks, their effectiveness…

Computer Vision and Pattern Recognition · Computer Science 2024-08-29 Chuang Niu , Christopher Wiedeman , Mengzhou Li , Jonathan S Maltz , Ge Wang

Diffusion Probabilistic Models (DPMs) have recently been employed for image deblurring, formulated as an image-conditioned generation process that maps Gaussian noise to the high-quality image, conditioned on the blurry input.…

Computer Vision and Pattern Recognition · Computer Science 2023-12-14 Mengwei Ren , Mauricio Delbracio , Hossein Talebi , Guido Gerig , Peyman Milanfar

We present a general method to analyze reverberation mapping data that provides both estimates for the black hole mass and for the geometry and dynamics of the broad line region (BLR) in active galactic nuclei (AGN). Our method directly…

Cosmology and Nongalactic Astrophysics · Physics 2015-05-27 Anna Pancoast , Brendon J. Brewer , Tommaso Treu

The Event Horizon Telescope (EHT) delivered the first image of a black hole by capturing the light from its surrounding accretion flow, revealing structure but not dynamics. Simulations of black hole accretion dynamics are essential for…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Renbo Tu , Ali SaraerToosi , Nicholas S. Conroy , Gennady Pekhimenko , Aviad Levis

Accurate dose distribution prediction is crucial in the radiotherapy planning. Although previous methods based on convolutional neural network have shown promising performance, they have the problem of over-smoothing, leading to prediction…

Image and Video Processing · Electrical Eng. & Systems 2024-10-31 Xin Liao , Zhenghao Feng , Jianghong Xiao , Xingchen Peng , Yan Wang

Unsupervised real-world super-resolution (SR) faces critical challenges due to the complex, unknown degradation distributions in practical scenarios. Existing methods struggle to generalize from synthetic low-resolution (LR) and…

Computer Vision and Pattern Recognition · Computer Science 2025-08-12 Hongyang Zhou , Xiaobin Zhu , Liuling Chen , Junyi He , Jingyan Qin , Xu-Cheng Yin , Zhang xiaoxing

We present a new code for performing general-relativistic radiation-hydrodynamics simulations of accretion flows onto black holes. The radiation field is treated in the optically-thick approximation, with the opacity contributed by Thomson…

High Energy Astrophysical Phenomena · Physics 2015-03-11 Olindo Zanotti , Constanze Roedig , Luciano Rezzolla , Luca Del Zanna

Blind face restoration (BFR) is important while challenging. Prior works prefer to exploit GAN-based frameworks to tackle this task due to the balance of quality and efficiency. However, these methods suffer from poor stability and…

Computer Vision and Pattern Recognition · Computer Science 2023-08-09 Xinmin Qiu , Congying Han , Zicheng Zhang , Bonan Li , Tiande Guo , Xuecheng Nie

Black holes (BHs) are believed to be a key ingredient of galaxy formation. However, the galaxy-BH interplay is challenging to study due to the large dynamical range and complex physics involved. As a consequence, hydrodynamical cosmological…

Astrophysics of Galaxies · Physics 2017-03-22 Andrea Negri , Marta Volonteri

The advent of high-fidelity imaging of supermassive black holes calls for efficient and robust data-analysis methods. In this work, we use $\texttt{Jipole}$, a differentiable, $\texttt{ipole}$-based radiative transfer code, to enable…

High Energy Astrophysical Phenomena · Physics 2026-04-15 Pedro Naethe Motta , Mário Raia Neto , Cora Prather , Alejandro Cárdenas-Avendaño

Generative models of graphs based on discrete Denoising Diffusion Probabilistic Models (DDPMs) offer a principled approach to molecular generation by systematically removing structural noise through iterative atom and bond adjustments.…

Machine Learning · Computer Science 2025-11-03 Matteo Ninniri , Marco Podda , Davide Bacciu

Diffusion probabilistic models (DPMs) and their extensions have emerged as competitive generative models yet confront challenges of efficient sampling. We propose a new bilateral denoising diffusion model (BDDM) that parameterizes both the…

Audio and Speech Processing · Electrical Eng. & Systems 2022-03-28 Max W. Y. Lam , Jun Wang , Dan Su , Dong Yu

We introduce the Fixed Point Diffusion Model (FPDM), a novel approach to image generation that integrates the concept of fixed point solving into the framework of diffusion-based generative modeling. Our approach embeds an implicit fixed…

Computer Vision and Pattern Recognition · Computer Science 2024-01-18 Xingjian Bai , Luke Melas-Kyriazi

We investigated the shadow and optical appearance of Bardeen black hole (BH) immersed in perfect-fluid dark matter (PFDM). Using the EHT data, we find that the DM parameter is restricted to a narrow allowed range, confined to values of…

High Energy Astrophysical Phenomena · Physics 2025-12-02 Haiyuan Feng , Ziqiang Cai , Hao-Peng Yan , Rong-Jia Yang , Jinjun Zhang