Search Results for author:
Found 79 papers, 25 papers with code
Simultaneous Diffusion Sampling for Conditional LiDAR Generation
Our method begins by recasting the input scan to multiple new viewpoints around the scan, thus creating multiple synthetic LiDAR scans.
Robust Scene Change Detection Using Visual Foundation Models and Cross-Attention Mechanisms
We present a novel method for scene change detection that leverages the robust feature extraction capabilities of a visual foundational model, DINOv2, and integrates full-image cross-attention to address key challenges such as varying lighting, seasonal variations, and viewpoint differences.
Test-Time Certifiable Self-Supervision to Bridge the Sim2Real Gap in Event-Based Satellite Pose Estimation
However, challenging lighting conditions due to strong directional light can still cause undesirable effects in the output of commercial off-the-shelf event sensors, such as noisy/spurious events and inhomogeneous event densities on the object.
Robust Fitting on a Gate Quantum Computer
In this paper, we take a big stride towards quantum robust fitting: we propose a quantum circuit to solve the $\ell_\infty$ feasibility test in the 1D case, which allows to demonstrate for the first time quantum robust fitting on a real gate quantum computer, the IonQ Aria.
Synthetic Lunar Terrain: A Multimodal Open Dataset for Training and Evaluating Neuromorphic Vision Algorithms
Synthetic Lunar Terrain (SLT) is an open dataset collected from an analogue test site for lunar missions, featuring synthetic craters in a high-contrast lighting setup.
TC-PDM: Temporally Consistent Patch Diffusion Models for Infrared-to-Visible Video Translation
Experiment shows that TC-PDM outperforms state-of-the-art methods by 35. 3% in FVD for infrared-to-visible video translation and by 6. 1% in AP50 for day-to-night object detection.
Weakly Supervised Test-Time Domain Adaptation for Object Detection
We propose to involve the operator in test-time domain adaptation to raise the performance of object detection beyond what is achievable by fully automated adaptation.
Camera-Pose Robust Crater Detection from Chang'e 5
This work provides the first quantitative analysis of performance of CDAs on images containing off-nadir view angles.
Event-based Structure-from-Orbit
Event sensors offer high temporal resolution visual sensing, which makes them ideal for perceiving fast visual phenomena without suffering from motion blur.
Projected Stochastic Gradient Descent with Quantum Annealed Binary Gradients
We present, QP-SBGD, a novel layer-wise stochastic optimiser tailored towards training neural networks with binary weights, known as binary neural networks (BNNs), on quantum hardware.
Domain Adaptation for Satellite-Borne Hyperspectral Cloud Detection
However, prior to deployment, new missions that employ new sensors will not have enough representative datasets to train a CNN model, while a model trained solely on data from previous missions will underperform when deployed to process the data on the new missions.
High Frequency, High Accuracy Pointing onboard Nanosats using Neuromorphic Event Sensing and Piezoelectric Actuation
In this work, we develop a novel payload that utilises a neuromorphic event sensor (for high frequency and highly accurate relative attitude estimation) paired in a closed loop with a piezoelectric stage (for active attitude corrections) to provide highly stable sensor-specific pointing.
Direct initial orbit determination
Initial orbit determination (IOD) is an important early step in the processing chain that makes sense of and reconciles the multiple optical observations of a resident space object.
Semantic Segmentation on 3D Point Clouds with High Density Variations
LiDAR scanning for surveying applications acquire measurements over wide areas and long distances, which produces large-scale 3D point clouds with significant local density variations.
Federated Neural Radiance Fields
The ability of neural radiance fields or NeRFs to conduct accurate 3D modelling has motivated application of the technique to scene representation.
Training Multilayer Perceptrons by Sampling with Quantum Annealers
This leads to a strategy to train MLPs with quantum annealers as a sampling engine.
Assessing Domain Gap for Continual Domain Adaptation in Object Detection
To ensure reliable object detection in autonomous systems, the detector must be able to adapt to changes in appearance caused by environmental factors such as time of day, weather, and seasons.
ROSIA: Rotation-Search-Based Star Identification Algorithm
This paper presents a rotation-search-based approach for addressing the star identification (Star-ID) problem.
Globally Optimal Event-Based Divergence Estimation for Ventral Landing
This is achieved by estimating divergence (inverse TTC), which is the rate of radial optic flow, from the event stream generated during landing.
Towards Bridging the Space Domain Gap for Satellite Pose Estimation using Event Sensing
Deep models trained using synthetic data require domain adaptation to bridge the gap between the simulation and target environments.
Update Compression for Deep Neural Networks on the Edge
In this paper, we consider the scenario where retraining can be done on the server side based on a copy of the DNN model, with only the necessary data transmitted to the edge to update the deployed model.
Asynchronous Optimisation for Event-based Visual Odometry
Event cameras open up new possibilities for robotic perception due to their low latency and high dynamic range.
A Hybrid Quantum-Classical Algorithm for Robust Fitting
While our usage of quantum computing does not surmount the fundamental intractability of robust fitting, by providing error bounds our algorithm is a practical improvement over randomised heuristics.
Adversarial Attacks against a Satellite-borne Multispectral Cloud Detector
In fact, advanced EO satellites perform deep learning-based cloud detection on board the satellites and downlink only clear-sky data to save precious bandwidth.
Maximum Consensus by Weighted Influences of Monotone Boolean Functions
In particular, we study endowing the Boolean cube with the Bernoulli measure and performing biased (as opposed to uniform) sampling.
Occlusion-Robust Object Pose Estimation with Holistic Representation
State-of-the-art (SOTA) object pose estimators take a two-stage approach, where the first stage predicts 2D landmarks using a deep network and the second stage solves for 6DOF pose from 2D-3D correspondences.
Ranked #2 on
6D Pose Estimation using RGB
on YCB-Video
Autonomy and Perception for Space Mining
Future Moon bases will likely be constructed using resources mined from the surface of the Moon.
Physical Adversarial Attacks on an Aerial Imagery Object Detector
In this work, we demonstrate one of the first efforts on physical adversarial attacks on aerial imagery, whereby adversarial patches were optimised, fabricated and installed on or near target objects (cars) to significantly reduce the efficacy of an object detector applied on overhead images.
Quantum Annealing Formulation for Binary Neural Networks
Quantum annealing is a promising paradigm for building practical quantum computers.
A Spacecraft Dataset for Detection, Segmentation and Parts Recognition
We also provide evaluations with state-of-the-art methods in object detection and instance segmentation as a benchmark for the dataset.
Learning to Predict Repeatability of Interest Points
Many robotics applications require interest points that are highly repeatable under varying viewpoints and lighting conditions.
Rotation Coordinate Descent for Fast Globally Optimal Rotation Averaging
Under mild conditions on the noise level of the measurements, rotation averaging satisfies strong duality, which enables global solutions to be obtained via semidefinite programming (SDP) relaxation.
Spatiotemporal Registration for Event-based Visual Odometry
The state-of-the-art method of contrast maximisation recovers the motion from a batch of events by maximising the contrast of the image of warped events.
Consensus Maximisation Using Influences of Monotone Boolean Functions
Consensus maximisation (MaxCon), which is widely used for robust fitting in computer vision, aims to find the largest subset of data that fits the model within some tolerance level.
Semantics for Robotic Mapping, Perception and Interaction: A Survey
In robotics and related research fields, the study of understanding is often referred to as semantics, which dictates what does the world "mean" to a robot, and is strongly tied to the question of how to represent that meaning.
A Chaos Theory Approach to Understand Neural Network Optimization
Then, we empirically show that for a large range of learning rates, SGD traverses the loss landscape across regions with largest eigenvalue of the Hessian similar to the inverse of the learning rate.
HM4: Hidden Markov Model with Memory Management for Visual Place Recognition
However, this creates an unboundedly-growing database that poses time and memory scalability challenges for place recognition methods.
Monocular Rotational Odometry with Incremental Rotation Averaging and Loop Closure
To simplify the task of absolute orientation estimation, we formulate the monocular rotational odometry problem and devise a fast algorithm to accurately estimate camera orientations with 2D-2D feature matches alone.
Quantum Robust Fitting
Many computer vision applications need to recover structure from imperfect measurements of the real world.
Auto-Rectify Network for Unsupervised Indoor Depth Estimation
However, excellent results have mostly been obtained in street-scene driving scenarios, and such methods often fail in other settings, particularly indoor videos taken by handheld devices.
Ranked #58 on
Monocular Depth Estimation
on NYU-Depth V2
Monotone Boolean Functions, Feasibility/Infeasibility, LP-type problems and MaxCon
This paper outlines connections between Monotone Boolean Functions, LP-Type problems and the Maximum Consensus Problem.
Topological Sweep for Multi-Target Detection of Geostationary Space Objects
In this paper, we propose a novel multi-target detection technique based on topological sweep, to find GEO objects from a short sequence of optical images.
Globally Optimal Contrast Maximisation for Event-based Motion Estimation
To alleviate this weakness, we propose a new globally optimal event-based motion estimation algorithm.
NeuRoRA: Neural Robust Rotation Averaging
Although the idea of replacing robust optimization methods by a graph-based network is demonstrated only for multiple rotation averaging, it could easily be extended to other graph-based geometric problems, for example, pose-graph optimization.
Resolving Marker Pose Ambiguity by Robust Rotation Averaging with Clique Constraints
Planar markers are useful in robotics and computer vision for mapping and localisation.
End-to-End Learnable Geometric Vision by Backpropagating PnP Optimization
To seamlessly combine deep learning and geometric vision, it is vital to perform learning and geometric optimization end-to-end.
Ranked #1 on
6D Pose Estimation using RGB
on LineMOD
(Accuracy metric)
Satellite Pose Estimation with Deep Landmark Regression and Nonlinear Pose Refinement
We propose an approach to estimate the 6DOF pose of a satellite, relative to a canonical pose, from a single image.
Consensus Maximization Tree Search Revisited
First, we show that the consensus maximization tree structure used previously actually contains paths that connect nodes at both adjacent and non-adjacent levels.
Scalable Place Recognition Under Appearance Change for Autonomous Driving
Our experiments show that, compared to state-of-the-art techniques, our method has much greater potential for large-scale place recognition for autonomous driving.
Event-based Star Tracking via Multiresolution Progressive Hough Transforms
A recent alternative is to use event sensors, which could enable more energy efficient and faster star trackers.
Visual SLAM: Why Bundle Adjust?
Bundle adjustment plays a vital role in feature-based monocular SLAM.
A Practical Maximum Clique Algorithm for Matching with Pairwise Constraints
An alternative approach is to directly search for the subset of correspondences that are pairwise consistent, without optimising the registration function.
Star Tracking using an Event Camera
Star trackers are primarily optical devices that are used to estimate the attitude of a spacecraft by recognising and tracking star patterns.
Practical optimal registration of terrestrial LiDAR scan pairs
Point cloud registration is a fundamental problem in 3D scanning.
Visual Localization Under Appearance Change: Filtering Approaches
Our approaches rely on local features with an encoding technique to represent an image as a single vector.
Deterministic consensus maximization with biconvex programming
In this paper, we propose an efficient deterministic optimization algorithm for consensus maximization.
G2D: from GTA to Data
This document describes G2D, a software that enables capturing videos from Grand Theft Auto V (GTA V), a popular role playing game set in an expansive virtual city.
A Fast Resection-Intersection Method for the Known Rotation Problem
The known rotation problem refers to a special case of structure-from-motion where the absolute orientations of the cameras are known.
Robust Fitting in Computer Vision: Easy or Hard?
Robust model fitting plays a vital role in computer vision, and research into algorithms for robust fitting continues to be active.
Guaranteed Outlier Removal for Point Cloud Registration with Correspondences
Our method significantly reduces the population of outliers, such that further optimization can be performed quickly.
Deterministic Approximate Methods for Maximum Consensus Robust Fitting
Further, our approach is naturally applicable to estimation problems with geometric residuals
Quasiconvex Plane Sweep for Triangulation With Outliers
Relative to the random sampling heuristic, our algorithm not only guarantees deterministic convergence to a local minimum, it typically achieves higher quality solutions in similar runtimes.
Coresets for Triangulation
A coreset possesses the special property that the error of the $\ell_{\infty}$ solution on the coreset is within known bounds from the global minimum.
An Exact Penalty Method for Locally Convergent Maximum Consensus
Our method is based on a formulating the problem with linear complementarity constraints, then defining a penalized version which is provably equivalent to the original problem.
Rotation Averaging and Strong Duality
In this paper we explore the role of duality principles within the problem of rotation averaging, a fundamental task in a wide range of computer vision applications.
A Branch-and-Bound Algorithm for Checkerboard Extraction in Camera-Laser Calibration
We formulate the checkerboard extraction as a combinatorial optimization problem with a clear cut objective function.
Clustering with Hypergraphs: The Case for Large Hyperedges
The extension of conventional clustering to hypergraph clustering, which involves higher order similarities instead of pairwise similarities, is increasingly gaining attention in computer vision.
Correspondence Insertion for As-Projective-As-Possible Image Stitching
However, estimating spatially varying warps requires a sufficient number of feature matches.
Conformal Surface Alignment With Optimal Mobius Search
Deformations of surfaces with the same intrinsic shape can often be described accurately by a conformal model.
Guaranteed Outlier Removal With Mixed Integer Linear Programs
Towards the goal of solving maximum consensus exactly, we present guaranteed outlier removal as a technique to reduce the runtime of exact algorithms.
A Consensus-Based Framework for Distributed Bundle Adjustment
In this paper we study large-scale optimization problems in multi-view geometry, in particular the Bundle Adjustment problem.
Efficient Point Process Inference for Large-Scale Object Detection
We tackle the problem of large-scale object detection in images, where the number of objects can be arbitrarily large, and can exhibit significant overlap/occlusion.
Guaranteed Outlier Removal for Rotation Search
Used as a preprocessor to prune a large portion of the outliers from the input data, our method enables substantial speed-up of rotation search algorithms without compromising global optimality.
The k-Support Norm and Convex Envelopes of Cardinality and Rank
Sparsity, or cardinality, as a tool for feature selection is extremely common in a vast number of current computer vision applications.
Efficient Globally Optimal Consensus Maximisation With Tree Search
We aim to change this state of affairs by proposing a very efficient algorithm for global maximisation of consensus.
Fast Rotation Search with Stereographic Projections for 3D Registration
In this work, assuming that the translation parameters are known, we focus on constructing a fast rotation search algorithm.
As-Projective-As-Possible Image Stitching with Moving DLT
We investigate projective estimation under model inadequacies, i. e., when the underpinning assumptions of the projective model are not fully satisfied by the data.
Simultaneous Sampling and Multi-Structure Fitting with Adaptive Reversible Jump MCMC
Multi-structure model fitting has traditionally taken a two-stage approach: First, sample a (large) number of model hypotheses, then select the subset of hypotheses that optimise a joint fitting and model selection criterion.
The Ordered Residual Kernel for Robust Motion Subspace Clustering
The kernel permits the application of well-established statistical learning methods for effective outlier rejection, automatic recovery of the number of motions and accurate segmentation of the point trajectories.
