The advent of satellite-borne machine learning hardware accelerators has...
As satellites become smaller, the ability to maintain stable pointing
de...
Initial orbit determination (IOD) is an important early step in the
proc...
LiDAR scanning for surveying applications acquire measurements over wide...
The ability of neural radiance fields or NeRFs to conduct accurate 3D
mo...
A successful application of quantum annealing to machine learning is tra...
Solving the star identification (Star-ID) problem with a
rotation-search...
Event sensing is a major component in bio-inspired flight guidance and
c...
Deep models trained using synthetic data require domain adaptation to br...
An increasing number of artificial intelligence (AI) applications involv...
Event cameras open up new possibilities for robotic perception due to th...
Fitting geometric models onto outlier contaminated data is provably
intr...
Data collected by Earth-observing (EO) satellites are often afflicted by...
Robust model fitting is a fundamental problem in computer vision: used t...
Practical object pose estimation demands robustness against occlusions t...
Future Moon bases will likely be constructed using resources mined from ...
Deep neural networks (DNNs) have become essential for processing the vas...
Quantum annealing is a promising paradigm for building practical quantum...
Virtually all aspects of modern life depend on space technology. Thanks ...
Many robotics applications require interest points that are highly repea...
Under mild conditions on the noise level of the measurements, rotation
a...
A useful application of event sensing is visual odometry, especially in
...
Consensus maximisation (MaxCon), which is widely used for robust fitting...
For robots to navigate and interact more richly with the world around th...
Visual place recognition needs to be robust against appearance variabili...
Estimating absolute camera orientations is essential for attitude estima...
Many computer vision applications need to recover structure from imperfe...
Single-view depth estimation using CNNs trained from unlabelled videos h...
This paper outlines connections between Monotone Boolean Functions, LP-T...
Conducting surveillance of the Earth's orbit is a key task towards achie...
Contrast maximisation estimates the motion captured in an event stream b...
Multiple rotation averaging is an essential task for structure from moti...
Planar markers are useful in robotics and computer vision for mapping an...
In this paper we present BPnP, a novel method to do back-propagation thr...
We propose an approach to estimate the 6DOF pose of a satellite, relativ...
Consensus maximization is widely used for robust fitting in computer vis...
A major challenge in place recognition for autonomous driving is to be r...
Star trackers are state-of-the-art attitude estimation devices which fun...
Bundle adjustment plays a vital role in feature-based monocular SLAM. In...
A popular paradigm for 3D point cloud registration is by extracting 3D
k...
Star trackers are primarily optical devices that are used to estimate th...
Point cloud registration is a fundamental problem in 3D scanning. In thi...
A major focus of current research on place recognition is visual localiz...
Consensus maximization is one of the most widely used robust fitting
par...
This document describes G2D, a software that enables capturing videos fr...
Robust model fitting plays a vital role in computer vision, and research...
An established approach for 3D point cloud registration is to estimate t...
Maximum consensus estimation plays a critically important role in robust...
Multiple-view triangulation by ℓ_∞ minimisation has become
established i...
In this paper we explore the role of duality principles within the probl...