Related papers: Simple Improved Reference Subtraction for H4RG, H2…

Reference-based image super-resolution (RefSR) represents a promising advancement in super-resolution (SR). In contrast to single-image super-resolution (SISR), RefSR leverages an additional reference image to help recover high-frequency…

Bright, coherent soft X-ray (SXR) radiation is essential to a variety of applications in fundamental research and life sciences. So far, high photon flux in this spectral region can only be delivered by synchrotrons, free electron lasers or…

Implicit Neural Representations (INRs) are increasingly recognized as a versatile data modality for representing discretized signals, offering benefits such as infinite query resolution and reduced storage requirements. Existing signal…

Referring Remote Sensing Image Segmentation (RRSIS) is critical for ecological monitoring, urban planning, and disaster management, requiring precise segmentation of objects in remote sensing imagery guided by textual descriptions. This…

In this paper we present seven techniques that everybody should know to improve example-based single image super resolution (SR): 1) augmentation of data, 2) use of large dictionaries with efficient search structures, 3) cascading, 4) image…

Next-generation intensity-modulation (IM) and direct-detection (DD) systems used in data centers are expected to operate at 400 Gb/s/lane and beyond. Such rates can be achieved by increasing the system bandwidth or the modulation format,…

Hyperspectral images (HSIs) provide exceptional spatial and spectral resolution of a scene, crucial for various remote sensing applications. However, the high dimensionality, presence of noise and outliers, and the need for precise labels…

For multiple index models, it has recently been shown that the sliced inverse regression (SIR) is consistent for estimating the sufficient dimension reduction (SDR) space if and only if $\rho=\lim\frac{p}{n}=0$, where $p$ is the dimension…

Single image super-resolution (SISR) is a notoriously challenging ill-posed problem, which aims to obtain a high-resolution (HR) output from one of its low-resolution (LR) versions. To solve the SISR problem, recently powerful deep learning…

We describe how the James Webb Space Telescope (JWST) Near-Infrared Spectrograph's (NIRSpec's) detectors will be read out, and present a model of how noise scales with the number of multiple non-destructive reads sampling-up-the-ramp. We…

Automated cardiac interpretation in resource-constrained settings (RCS) is often hindered by poor-quality echocardiographic imaging, limiting the effectiveness of downstream diagnostic models. While super-resolution (SR) techniques have…

This paper proposes a simple, accurate, and robust approach to single image nonparametric blind Super-Resolution (SR). This task is formulated as a functional to be minimized with respect to both an intermediate super-resolved image and a…

To reduce the storage requirements, remote sensing (RS) images are usually stored in compressed format. Existing scene classification approaches using deep neural networks (DNNs) require to fully decompress the images, which is a…

Accurate reconstruction of temperature field of heat-source systems (TFR-HSS) is crucial for thermal monitoring and reliability assessment in engineering applications such as electronic devices and aerospace structures. However, the high…

Composed Image Retrieval (CIR) aims to retrieve a target image based on a reference image and conditioning text, enabling controllable image searches. The mainstream Zero-Shot (ZS) CIR methods bypass the need for expensive training CIR…

Photodetectors converting light signals into detectable photocurrents are ubiquitously in use today. To improve the compactness and performance of next-generation devices and systems, low dimensional materials provide rich physics to…

Superpixels have long been used in image simplification to enable more efficient data processing and storage. However, despite their computational potential, their irregular spatial distribution has often forced deep learning approaches to…

Interactive reflecting surfaces (IRSs) are a remarkable technology that will be integrated into 6G wireless networks to enhance the electromagnetic propagation environment in a programmable or adaptable way in order to improve communication…

Diffuse direct time-of-flight LiDARs report per-pixel depth histograms formed by aggregating photon returns over a wide instantaneous field of view, violating the single-ray assumption behind standard LiDAR-RGB calibration. We present a…

Hybrid Foreground Residual Subtraction (HyFoReS) is a new family of algorithms designed to remove systematics-induced foreground contamination for 21-cm intensity mapping data. Previously, the algorithm was shown to be effective in…