Related papers: HelioFill: Diffusion-Based Model for EUV Reconstru…
Extra-solar planets have not been imaged directly with existing ground or space telescopes because they are too faint to be seen against the halo of the nearby bright star. Most techniques being explored to suppress the halo are achromatic,…
Previous raw image-based low-light image enhancement methods predominantly relied on feed-forward neural networks to learn deterministic mappings from low-light to normally-exposed images. However, they failed to capture critical…
Fluorescence microscopy (FM) imaging is a fundamental technique for observing live cell division, one of the most essential processes in the cycle of life and death. Observing 3D live cells requires scanning through the cell volume while…
Deep image restoration models aim to learn a mapping from degraded image space to natural image space. However, they face several critical challenges: removing degradation, generating realistic details, and ensuring pixel-level consistency.…
Heliospheric imagers offer the promise of remote sensing of large-scale structures present in the solar wind. The STEREO/HI-2 imagers, in particular, offer high resolution, very low noise observations of the inner heliosphere but have not…
Since its launch on 22 September 2006, the EUV Imaging Spectrometer onboard the Hinode satellite has exhibited a gradual decay in sensitivity. Using spectroheliograms taken in the Fe VIII 185.21 Angstrom and Si VII 275.35 Angstrom emission…
Old-photo face restoration poses significant challenges due to compounded degradations such as breakage, fading, and severe blur. Existing pre-trained diffusion-guided methods either rely on explicit degradation priors or global statistical…
Electron backscatter diffraction (EBSD) has developed over the last few decades into a valuable crystallographic characterisation method for a wide range of sample types. Despite these advances, issues such as the complexity of sample…
Point clouds are widely used for infrastructure monitoring by providing geometric information, where segmentation is required for downstream tasks such as defect detection. Existing research has automated semantic segmentation of structural…
Solar activity during 2007--2009 was very low, causing anomalously low thermospheric density. A comparison of solar extreme ultraviolet (EUV) irradiance in the He II spectral band (26 to 34 nm) from the Solar Extreme ultraviolet Monitor…
Spatial Transcriptomics (ST) allows a high-resolution measurement of RNA sequence abundance by systematically connecting cell morphology depicted in Hematoxylin and Eosin (H&E) stained histology images to spatially resolved gene…
We propose DiffuStereo, a novel system using only sparse cameras (8 in this work) for high-quality 3D human reconstruction. At its core is a novel diffusion-based stereo module, which introduces diffusion models, a type of powerful…
The dust in nearby galaxies absorbs a fraction of the UV-optical-near-infrared radiation produced by stars. This energy is consequently re-emitted in the infrared. We investigate the portion of the stellar radiation absorbed by spiral…
In this two-part paper, we present a novel framework and methodology to analyze data from certain image-based biochemical assays, e.g., ELISPOT and Fluorospot assays. In this first part, we start by presenting a physical partial…
Digital Surface Models (DSMs) are essential for accurately representing Earth's topography in geospatial analyses. DSMs capture detailed elevations of natural and manmade features, crucial for applications like urban planning, vegetation…
Observations the Sun's photospheric magnetic field are often confined to the Sun-Earth line. Surface flux transport (SFT) models, such as the Advective Flux Transport (AFT) model, simulate the evolution of the photospheric magnetic field to…
We present the first results from the HST Archival Legacy project "SKYSURF." As described in Windhorst et al. 2022, SKYSURF utilizes the large HST archive to study the diffuse UV, optical, and near-IR backgrounds and foregrounds in detail.…
Denoising diffusion models are a powerful type of generative models used to capture complex distributions of real-world signals. However, their applicability is limited to scenarios where training samples are readily available, which is not…
The STEREO mission has been providing stereoscopic view of filament eruptions in EUV. The clearest view during a filament eruption is seen in He II 304 A observations. One of the main problems visualizing filament dynamics in He II 304 A is…
Bird's-eye-view (BEV) representations play a crucial role in autonomous driving tasks. Despite recent advancements in BEV generation, inherent noise, stemming from sensor limitations and the learning process, remains largely unaddressed,…