Related papers: Development of a High Fidelity Simulator for Gener…
In recent years, deep learning models have been successfully employed for augmenting low-resolution cosmological simulations with small-scale information, a task known as "super-resolution". So far, these cosmological super-resolution…
The creation of accurate virtual models of real-world objects is imperative to robotic simulations and applications such as computer vision, artificial intelligence, and machine learning. This paper documents the different methods employed…
Small object detection (SOD) is a critical yet challenging task in computer vision, with applications like spanning surveillance, autonomous systems, medical imaging, and remote sensing. Unlike larger objects, small objects contain limited…
We propose a methodology for lidar super-resolution with ground vehicles driving on roadways, which relies completely on a driving simulator to enhance, via deep learning, the apparent resolution of a physical lidar. To increase the…
We explore the capability of deep learning to classify cosmic structures. In cosmological simulations, cosmic volumes are segmented into voids, sheets, filaments and knots, according to the distribution and kinematics of dark matter (DM),…
Identifying predictive world models for robots in novel environments from sparse online observations is essential for robot task planning and execution in novel environments. However, existing methods that leverage differentiable…
The rapid progress in machine learning models has significantly boosted the potential for real-world applications such as autonomous vehicles, disease diagnoses, and recognition of emergencies. The performance of many machine learning…
Image Processing algorithms for vision-based navigation require reliable image simulation capacities. In this paper we explain why traditional rendering engines may present limitations that are potentially critical for space applications.…
We consider the problem in Synthetic Aperture RADAR (SAR) of identifying and classifying objects located on the ground by means of Convolutional Neural Networks (CNNs). Specifically, we adopt a single scattering approximation to classify…
Non-Line-of-Sight (NLOS) imaging reconstructs the shape and depth of hidden objects from picosecond-resolved transient signals, offering potential applications in autonomous driving, security, and medical diagnostics. However, current NLOS…
In recent years, machine learning (ML) has gained significant popularity in the field of chemical informatics and electronic structure theory. These techniques often require researchers to engineer abstract "features" that encode chemical…
Most of the existing learning-based single image superresolution (SISR) methods are trained and evaluated on simulated datasets, where the low-resolution (LR) images are generated by applying a simple and uniform degradation (i.e., bicubic…
Generative deep learning methods built upon Convolutional Neural Networks (CNNs) provide a great tool for predicting non-linear structure in cosmology. In this work we predict high resolution dark matter halos from large scale, low…
The rapid advancement of deep generative models (DGMs) has significantly advanced research in computer vision, providing a cost-effective alternative to acquiring vast quantities of expensive imagery. However, existing methods predominantly…
Image acquisition conditions and environments can significantly affect high-level tasks in computer vision, and the performance of most computer vision algorithms will be limited when trained on distortion-free datasets. Even with updates…
We present a novel approach to adjust global image properties such as colour, saturation, and luminance using human-interpretable image enhancement curves, inspired by the Photoshop curves tool. Our method, dubbed neural CURve Layers…
Object co-segmentation is to segment the shared objects in multiple relevant images, which has numerous applications in computer vision. This paper presents a spatial and semantic modulated deep network framework for object co-segmentation.…
Deep learning has enabled remarkable advances in scene understanding, particularly in semantic segmentation tasks. Yet, current state of the art approaches are limited to a closed set of classes, and fail when facing novel elements, also…
Current approaches to semantic image and scene understanding typically employ rather simple object representations such as 2D or 3D bounding boxes. While such coarse models are robust and allow for reliable object detection, they discard…
Posterior inference from pulsar observations in the form of light curves is commonly performed using Markov chain Monte Carlo methods, which are accurate but computationally expensive. We introduce a framework that accelerates posterior…