11 citations · 32 across the 23 of their papers we have counts for
25 papers
SpecBPP: A Self-Supervised Learning Approach for Hyperspectral Representation and Soil Organic Carbon Estimation
Daniel La'ah Ayuba, Jean-Yves Guillemaut, Belen Marti-Cardona +1
Self-supervised learning has revolutionized representation learning in vision and language, but remains underexplored for hyperspectral imagery (HSI), where the sequential structur…
HuGeDiff: 3D Human Generation via Diffusion with Gaussian Splatting
Maksym Ivashechkin, Oscar Mendez, Richard Bowden
3D human generation is an important problem with a wide range of applications in computer vision and graphics. Despite recent progress in generative AI such as diffusion models or…
SignSplat: Rendering Sign Language via Gaussian Splatting
Maksym Ivashechkin, Oscar Mendez, Richard Bowden
State-of-the-art approaches for conditional human body rendering via Gaussian splatting typically focus on simple body motions captured from many views. This is often in the contex…
HandOcc: NeRF-based Hand Rendering with Occupancy Networks
Maksym Ivashechkin, Oscar Mendez, Richard Bowden
We propose HandOcc, a novel framework for hand rendering based upon occupancy. Popular rendering methods such as NeRF are often combined with parametric meshes to provide deformabl…
The Radiance of Neural Fields: Democratizing Photorealistic and Dynamic Robotic Simulation
Georgina Nuthall, Richard Bowden, Oscar Mendez
As robots increasingly coexist with humans, they must navigate complex, dynamic environments rich in visual information and implicit social dynamics, like when to yield or move thr…
Two Hands Are Better Than One: Resolving Hand to Hand Intersections via Occupancy Networks
Maksym Ivashechkin, Oscar Mendez, Richard Bowden
3D hand pose estimation from images has seen considerable interest from the literature, with new methods improving overall 3D accuracy. One current challenge is to address hand-to-…
RaSpectLoc: RAman SPECTroscopy-dependent robot LOCalisation
Christopher Thomas Thirgood, Oscar Alejandro Mendez Maldonado, Chao Ling +2
This paper presents a new information source for supporting robot localisation: material composition. The proposed method complements the existing visual, structural, and semantic…
Improving 3D Pose Estimation for Sign Language
Maksym Ivashechkin, Oscar Mendez, Richard Bowden
This work addresses 3D human pose reconstruction in single images. We present a method that combines Forward Kinematics (FK) with neural networks to ensure a fast and valid predict…
Denoising Diffusion for 3D Hand Pose Estimation from Images
Maksym Ivashechkin, Oscar Mendez, Richard Bowden
Hand pose estimation from a single image has many applications. However, approaches to full 3D body pose estimation are typically trained on day-to-day activities or actions. As su…
Learning Adaptive Neighborhoods for Graph Neural Networks
Avishkar Saha, Oscar Mendez, Chris Russell +1
Graph convolutional networks (GCNs) enable end-to-end learning on graph structured data. However, many works assume a given graph structure. When the input graph is noisy or unavai…
G-CMP: Graph-enhanced Contextual Matrix Profile for unsupervised anomaly detection in sensor-based remote health monitoring
Nivedita Bijlani, Oscar Mendez Maldonado, Samaneh Kouchaki
Sensor-based remote health monitoring is used in industrial, urban and healthcare settings to monitor ongoing operation of equipment and human health. An important aim is to interv…
AFT-VO: Asynchronous Fusion Transformers for Multi-View Visual Odometry Estimation
Nimet Kaygusuz, Oscar Mendez, Richard Bowden
Motion estimation approaches typically employ sensor fusion techniques, such as the Kalman Filter, to handle individual sensor failures. More recently, deep learning-based fusion a…
Generalizing to New Tasks via One-Shot Compositional Subgoals
Xihan Bian, Oscar Mendez, Simon Hadfield
The ability to generalize to previously unseen tasks with little to no supervision is a key challenge in modern machine learning research. It is also a cornerstone of a future "Gen…
SKILL-IL: Disentangling Skill and Knowledge in Multitask Imitation Learning
Bian Xihan, Oscar Mendez, Simon Hadfield
In this work, we introduce a new perspective for learning transferable content in multi-task imitation learning. Humans are able to transfer skills and knowledge. If we can cycle t…
"The Pedestrian next to the Lamppost" Adaptive Object Graphs for Better Instantaneous Mapping
Avishkar Saha, Oscar Mendez, Chris Russell +1
Estimating a semantically segmented bird's-eye-view (BEV) map from a single image has become a popular technique for autonomous control and navigation. However, they show an increa…
Multi-Camera Sensor Fusion for Visual Odometry using Deep Uncertainty Estimation
Nimet Kaygusuz, Oscar Mendez, Richard Bowden
Visual Odometry (VO) estimation is an important source of information for vehicle state estimation and autonomous driving. Recently, deep learning based approaches have begun to ap…
MDN-VO: Estimating Visual Odometry with Confidence
Nimet Kaygusuz, Oscar Mendez, Richard Bowden
Visual Odometry (VO) is used in many applications including robotics and autonomous systems. However, traditional approaches based on feature matching are computationally expensive…
Translating Images into Maps
Avishkar Saha, Oscar Mendez Maldonado, Chris Russell +1
We approach instantaneous mapping, converting images to a top-down view of the world, as a translation problem. We show how a novel form of transformer network can be used to map f…
Improving Robot Localisation by Ignoring Visual Distraction
Oscar Mendez, Matthew Vowels, Richard Bowden
Attention is an important component of modern deep learning. However, less emphasis has been put on its inverse: ignoring distraction. Our daily lives require us to explicitly avoi…
Robot in a China Shop: Using Reinforcement Learning for Location-Specific Navigation Behaviour
Xihan Bian, Oscar Mendez, Simon Hadfield
Robots need to be able to work in multiple different environments. Even when performing similar tasks, different behaviour should be deployed to best fit the current environment. I…
Markov Localisation using Heatmap Regression and Deep Convolutional Odometry
Oscar Mendez, Simon Hadfield, Richard Bowden
In the context of self-driving vehicles there is strong competition between approaches based on visual localisation and LiDAR. While LiDAR provides important depth information, it…
A Robust Extrinsic Calibration Framework for Vehicles with Unscaled Sensors
Celyn Walters, Oscar Mendez, Simon Hadfield +1
Accurate extrinsic sensor calibration is essential for both autonomous vehicles and robots. Traditionally this is an involved process requiring calibration targets, known fiducial…
There and Back Again: Self-supervised Multispectral Correspondence Estimation
Celyn Walters, Oscar Mendez, Mark Johnson +1
Across a wide range of applications, from autonomous vehicles to medical imaging, multi-spectral images provide an opportunity to extract additional information not present in colo…
Localisation via Deep Imagination: learn the features not the map
Jaime Spencer, Oscar Mendez, Richard Bowden +1
How many times does a human have to drive through the same area to become familiar with it? To begin with, we might first build a mental model of our surroundings. Upon revisiting…