Learning-based methods to solve dense 3D vision problems typically train...
Depth estimation is a core task in 3D computer vision. Recent methods
in...
In this work, we study how well different type of approaches generalise ...
State-of-the-art methods for 6D object pose estimation typically train a...
Current 6D object pose methods consist of deep CNN models fully optimize...
Unusual events are important as being possible indicators of undesired
c...