相关论文: Edge-Aware Extended Star-Tetrix Transforms for CFA…
Previous methods for dynamic facial expression in the wild are mainly based on Convolutional Neural Networks (CNNs), whose local operations ignore the long-range dependencies in videos. To solve this problem, we propose the spatio-temporal…
The highly luminous (> 10^37 erg s^-1) supersoft X-ray sources (SSS) are believed to be Eddington limited accreting white dwarfs undergoing surface hydrogen burning. The current paradigm for SSS involves thermally unstable mass transfer…
Transmission spectroscopy is currently the technique best suited to study a wide range of planetary atmospheres, leveraging the filtering of a star's light by a planet's atmosphere rather than its own emission. However, as both a planet and…
sRGB images are now the predominant choice for pre-training visual models in computer vision research, owing to their ease of acquisition and efficient storage. Meanwhile, the advantage of RAW images lies in their rich physical information…
Hyperspectral images, which record the electromagnetic spectrum for a pixel in the image of a scene, often store hundreds of channels per pixel and contain an order of magnitude more information than a typical similarly-sized color image.…
A variety of on-orbit imaging and spectroscopic observations are used to characterize the Charge Transfer Efficiency (CTE) of the Charge-Coupled Device (CCD) of the Space Telescope Imaging Spectrograph (STIS) aboard the Hubble Space…
Image-to-image translation has been revolutionized with GAN-based methods. However, existing methods lack the ability to preserve the identity of the source domain. As a result, synthesized images can often over-adapt to the reference…
In recent years, deep networks have led to dramatic improvements in speech enhancement by framing it as a data-driven pattern recognition problem. In many modern enhancement systems, large amounts of data are used to train a deep network to…
It is an ill-posed problem to recover the true scene colors from a color biased image by discounting the effects of scene illuminant and camera spectral sensitivity (CSS) at the same time. Most color constancy (CC) models have been designed…
Photo-z algorithms that utilize SED template fitting have matured, and are widely adopted for use on high-redshift near-infrared data that provides a unique window into the early universe. Alternative photo-z methods have been developed,…
Semantic communication has undergone considerable evolution due to the recent rapid development of artificial intelligence (AI), significantly enhancing both communication robustness and efficiency. Despite these advancements, most current…
Video inpainting aims to fill the given spatiotemporal holes with realistic appearance but is still a challenging task even with prosperous deep learning approaches. Recent works introduce the promising Transformer architecture into deep…
The Image-Based Rendering (IBR) approach using Shearlet Transform (ST) is one of the most effective methods for Densely-Sampled Light Field (DSLF) reconstruction. The ST-based DSLF reconstruction typically relies on an iterative…
Linear phase-contrast scanning transmission electron microscopy (STEM) techniques compatible with high-throughput 4D-STEM acquisition are widely used to enhance phase contrast in weakly scattering and beam-sensitive materials. In these…
A significant challenge in the field of object detection lies in the system's performance under non-ideal imaging conditions, such as rain, fog, low illumination, or raw Bayer images that lack ISP processing. Our study introduces "Feature…
Photometric light curves suffer from fundamental degeneracies that limit surface information recovery. We demonstrate that astrometry enables access to complementary information through photocentre variations induced by rotating surface…
Space-based direct imaging provides prospects for detection and spectral characterization of exoplanets at optical and near-infrared wavelengths. Integral field spectrographs (IFS) have been historically baselined for these mission…
In this paper, we introduce a low-complexity approximation for the discrete Tchebichef transform (DTT). The proposed forward and inverse transforms are multiplication-free and require a reduced number of additions and bit-shifting…
Monte Carlo radiative transfer (MCRT) simulations are a powerful tool for determining the appearance of astrophysical objects, analyzing the prevalent physical conditions within them, and inferring their properties on the basis of real…
Fourier transform methods are used to analyze functions and data sets to provide frequencies, amplitudes, and phases of underlying oscillatory components. Fast Fourier transform (FFT) methods offer speed advantages over evaluation of…