Related papers: Gnuastro: visualizing the full dynamic range in co…
We present InvRGB+L, a novel inverse rendering model that reconstructs large, relightable, and dynamic scenes from a single RGB+LiDAR sequence. Conventional inverse graphics methods rely primarily on RGB observations and use LiDAR mainly…
In this paper we show how advanced visualization tools can help the researcher in investigating and extracting information from data. The focus is on VisIVO, a novel open source graphics application, which blends high performance…
We present the Colorization Transformer, a novel approach for diverse high fidelity image colorization based on self-attention. Given a grayscale image, the colorization proceeds in three steps. We first use a conditional autoregressive…
Accurate and automated galaxy redshift determination is essential for maximizing the scientific return of spectroscopic surveys. In this paper, we propose a data-driven method to address this challenge. The method first learns a rest-frame…
The PICsIT detector onboard the INTEGRAL satellite was designed to provide information about emission in the soft gamma-ray band for many bright sources. Due to strong and variable instrumental background, only 4 objects have been detected…
Polarization images provide rich physical information that is fundamentally absent from standard RGB images, benefiting a wide range of computer vision applications such as reflection separation and material classification. However, the…
In the big data era of Astrophysics, the improvement of visualization techniques can greatly enhance the ability to identify and interpret key features in complex datasets. This aspect of data analysis will become even more relevant in the…
Radiance field reconstruction aims to recover high-quality 3D representations from multi-view RGB images. Recent advances, such as 3D Gaussian splatting, enable real-time rendering with high visual fidelity on sufficiently powerful graphics…
Interpretation of data from faint dwarf galaxies is made challenging by observations limited to only the brightest stars. We present a major improvement to tackle this challenge by undertaking zoomed cosmological simulations that resolve…
Given an observed gravitational lens mirage produced by a foreground deflector (cf. galaxy, quasar, cluster,...), it is possible via numerical lens inversion to retrieve the real source image, taking full advantage of the magnifying power…
Document image enhancement and binarization methods are often used to improve the accuracy and efficiency of document image analysis tasks such as text recognition. Traditional non-machine-learning methods are constructed on low-level…
Hyperspectral imaging offers new perspectives for diverse applications, ranging from the monitoring of the environment using airborne or satellite remote sensing, precision farming, food safety, planetary exploration, or astrophysics.…
Spectangular is a GUI based software package written in C++ designed for spectral disentangling on the wavelength scale. The code disentangles spectra of SB1 and SB2 systems and can now also be used also for spectra showing variability. In…
This work presents an unsupervised deep learning scheme that exploiting high-dimensional assisted score-based generative model for color image restoration tasks. Considering that the sample number and internal dimension in score-based…
Varying only the in-plane or out-of-plane dimensions of nanostructures produces a wide range of colourful elements in metasurfaces and thin films. However, achieving shades of grey and control of colour saturation remains challenging. Here,…
We propose a new, efficient multi-scale method to decompose a map (or signal in general) into components maps that contain structures of different sizes. In the widely-used wave transform, artifacts containing negative values arise around…
Digital co-addition of astronomical images is a common technique for increasing signal-to-noise and image depth. A modification of this simple technique has been applied to the detection of minor bodies in the Solar System: first stationary…
Image datasets such as MNIST are a key benchmark for testing Graph Neural Network (GNN) architectures. The images are traditionally represented as a grid graph with each node representing a pixel and edges connecting neighboring pixels…
Gravitational lensing allows us to probe the structure of matter on a broad range of astronomical scales, and as light from a distant source traverses an intervening galaxy, compact matter such as planets, stars, and black holes act as…
Increasingly there is a need to develop astronomical visualisation and manipulations tools which allow viewers to interact with displayed data directly, in real time and across a range of platforms. In addition, increases in dynamic range…