An accurate and uncertainty-aware 3D human body pose estimation is key t...
Robust, fast, and accurate human state - 6D pose and posture - estimatio...
While deep reinforcement learning (RL) agents outperform humans on an
in...
We present a real-time visual-inertial dense mapping method capable of
p...
Incrementally recovering 3D dense structures from monocular videos is of...
Exploration of unknown space with an autonomous mobile robot is a
well-s...
Visual reconstruction of fast non-rigid object deformations over time is...
In this paper, we propose a novel object-level mapping system that can
s...
In this paper, we present a tightly-coupled visual-inertial object-level...
Robotic applications are continuously striving towards higher levels of
...
The best way to combine the results of deep learning with standard 3D
re...
While the keypoint-based maps created by sparse monocular simultaneous
l...
While dense visual SLAM methods are capable of estimating dense
reconstr...
Estimating human motion from video is an active research area due to its...
We propose a keypoint-based object-level SLAM framework that can provide...
By estimating 3D shape and instances from a single view, we can capture
...
Semantic labelling is highly correlated with geometry and radiance
recon...
In robotic applications, a key requirement for safe and efficient motion...
We present an efficient, elastic 3D LiDAR reconstruction framework which...
With the aim of bridging the gap between high quality reconstruction and...
Dense image alignment from RGB-D images remains a critical issue for
rea...
Aerial manipulation aims at combining the manoeuvrability of aerial vehi...
Graph processors such as Graphcore's Intelligence Processing Unit (IPU) ...
Generally capable Spatial AI systems must build persistent scene
represe...
In this work we introduce a new bounding-box free network (BBFNet) for
p...
Safe and precise reference tracking is a crucial characteristic of MAVs ...
Exploration and collision-free navigation through an unknown environment...
Event cameras are bio-inspired sensors that work radically different fro...
Systems which incrementally create 3D semantic maps from image sequences...
Systems which incrementally create 3D semantic maps from image sequences...
Detailed 3D reconstruction is an important challenge with application to...
We propose a new multi-instance dynamic RGB-D SLAM system using an
objec...
Sum-of-squares objective functions are very popular in computer vision
a...
Datasets have gained an enormous amount of popularity in the computer vi...
We propose an online object-level SLAM system which builds a persistent ...
Incorporating the physical environment is essential for a complete
under...
The representation of geometry in real-time 3D perception systems contin...
We introduce SceneNet RGB-D, expanding the previous work of SceneNet to
...
Ever more robust, accurate and detailed mapping using visual sensing has...
This paper presents a new method for parallel-jaw grasping of isolated
o...
A multi-view image sequence provides a much richer capacity for object
r...