T
Thomas Whelan
Researcher at Maynooth University
Publications - 31
Citations - 5022
Thomas Whelan is an academic researcher from Maynooth University. The author has contributed to research in topics: Point cloud & Visual odometry. The author has an hindex of 19, co-authored 31 publications receiving 4165 citations. Previous affiliations of Thomas Whelan include Imperial College London & Facebook.
Papers
More filters
Proceedings ArticleDOI
A benchmark for RGB-D visual odometry, 3D reconstruction and SLAM
TL;DR: This work introduces the Imperial College London and National University of Ireland Maynooth (ICL-NUIM) dataset and presents a collection of handheld RGB-D camera sequences within synthetically generated environments to provide a method to benchmark the surface reconstruction accuracy.
Proceedings ArticleDOI
ElasticFusion: Dense SLAM Without A Pose Graph
TL;DR: This system is capable of capturing comprehensive dense globally consistent surfel-based maps of room scale environments explored using an RGB-D camera in an incremental online fashion, without pose graph optimisation or any postprocessing steps.
Proceedings Article
Kintinuous: Spatially Extended KinectFusion
TL;DR: An extension to the KinectFusion algorithm that permits dense mesh-based mapping of extended scale environments in real-time and a comparison between the two approaches where a trade off between the reduced drift of the visual odometry approach and the higher local mesh quality of the ICP-based approach is provided.
Journal ArticleDOI
ElasticFusion: Real-time dense SLAM and light source estimation
TL;DR: It is shown that a novel approach to real-time dense visual simultaneous localisation and mapping enables more realistic augmented reality rendering; a richer understanding of the scene beyond pure geometry and more accurate and robust photometric tracking.
Journal ArticleDOI
Real-time large-scale dense RGB-D SLAM with volumetric fusion
TL;DR: In this article, a volumetric fusion-based surface reconstruction system for real-time SLAM is presented. But the system is limited to a single RGB-D sensor.