Related papers: Generation of Imaging Air Cherenkov Telescope imag…
Speech super-resolution (SR) is the task that restores high-resolution speech from low-resolution input. Existing models employ simulated data and constrained experimental settings, which limit generalization to real-world SR. Predictive…
Recent advancements in diffusion models have been effective in learning data priors for solving inverse problems. They leverage diffusion sampling steps for inducing a data prior while using a measurement guidance gradient at each step to…
Imaging atmospheric Cherenkov telescopes (IACTs) are used to observe very high-energy photons from the ground. Gamma rays are indirectly detected through the Cherenkov light emitted by the air showers they induce. The new generation of…
Diffusion models offer stable training and state-of-the-art performance for deep generative modeling tasks. Here, we consider their use in the context of multivariate subsurface modeling and probabilistic inversion. We first demonstrate…
Spatial profiling technologies in biology, such as imaging mass cytometry (IMC) and spatial transcriptomics (ST), generate high-dimensional, multi-channel data with strong spatial alignment and complex inter-channel relationships.…
We present a novel method for exemplar-based image translation, called matching interleaved diffusion models (MIDMs). Most existing methods for this task were formulated as GAN-based matching-then-generation framework. However, in this…
Photoacoustic tomography (PAT) is a rapidly-evolving medical imaging modality that combines optical absorption contrast with ultrasound imaging depth. One challenge in PAT is image reconstruction with inadequate acoustic signals due to…
The efficiency of the $\gamma$/hadron separation worsens significantly at low energies for Imaging Air Cherenkov Telescopes (IACT). This observed effect was partially explained by the occurrence of a hardly reducible hadronic background…
Simulating showers of particles in highly-granular calorimeters is a key frontier in the application of machine learning to particle physics. Achieving high accuracy and speed with generative machine learning models can enable them to…
The generative priors of pre-trained latent diffusion models (DMs) have demonstrated great potential to enhance the visual quality of image super-resolution (SR) results. However, the noise sampling process in DMs introduces randomness in…
During the last decade, imaging atmospheric Cherenkov telescopes (IACTs) have proven themselves as astronomical detectors in the very-high-energy (VHE; E>0.1 TeV) regime. The IACT technique observes the VHE photons indirectly, using the…
Text-to-image (T2I) diffusion models lack an efficient mechanism for early quality assessment, leading to costly trial-and-error in multi-generation scenarios such as prompt iteration, agent-based generation, and flow-grpo. We reveal a…
The reconstruction of X-rays CT images from sparse or limited-angle geometries is a highly challenging task. The lack of data typically results in artifacts in the reconstructed image and may even lead to object distortions. For this…
We present studies for optimizing the next generation of ground-based imaging atmospheric Cherenkov telescopes (IACTs). Results focus on mid-sized telescopes (MSTs) for CTA, detecting very high energy gamma rays in the energy range from a…
Ground-based gamma-ray astronomy aims at reconstructing the energy and direction of gamma rays from the extensive air showers they initiate in the atmosphere. Imaging Atmospheric Cherenkov Telescopes (IACT) collect the Cherenkov light…
Generative adversarial networks (GANs) are frequently utilized in astronomy to construct an emulator of numerical simulations. Nevertheless, training GANs can prove to be a precarious task, as they are prone to instability and often lead to…
High energy cosmic-rays generate air showers when they enter Earth's atmosphere. Ground-based gamma-ray astronomy is possible using either direct detection of shower particles at mountain altitudes, or with arrays of imaging air-Cherenkov…
We introduce a framework for joint grounded scene graph - image generation, a challenging task involving high-dimensional, multi-modal structured data. To effectively model this complex joint distribution, we adopt a factorized approach:…
The recent wave of large-scale text-to-image diffusion models has dramatically increased our text-based image generation abilities. These models can generate realistic images for a staggering variety of prompts and exhibit impressive…
During the last decade ground-based very high-energy gamma-ray astronomy achieved a remarkable advancement in the development of the observational technique for the registration and study of gamma-ray emission above 100 GeV. It is widely…