Deep learning has led to great progress in the detection of mobile (i.e....
Self-supervised deep learning methods for joint depth and ego-motion
est...
Unmanned aerial vehicles (UAVs) have been used for many applications in
...
Long-term camera re-localization is an important task with numerous comp...
Miscalibration – a mismatch between a model's confidence and its correct...
Obtaining highly accurate depth from stereo images in real time has many...
Many applications require a camera to be relocalised online, without
exp...
Instance segmentation is an important problem in computer vision, with
a...
Stereo depth estimation is used for many computer vision applications. T...
Camera pose estimation is an important problem in computer vision. Commo...
Reconstructing dense, volumetric models of real-world 3D scenes is impor...
Volumetric models have become a popular representation for 3D scenes in
...
Camera relocalisation is an important problem in computer vision, with
a...
Current object detection approaches predict bounding boxes, but these pr...
It is not always possible to recognise objects and infer material proper...
Correlation Filter-based trackers have recently achieved excellent
perfo...
We present an open-source, real-time implementation of SemanticPaint, a
...