4 papers · 1 filter
N-QGN: Navigation Map from a Monocular Camera using Quadtree Generating Networks
Daniel Braun, Olivier Morel, Pascal Vasseur +1
Monocular depth estimation has been a popular area of research for several years, especially since self-supervised networks have shown increasingly good results in bridging the gap…
Towards urban scenes understanding through polarization cues
Marc Blanchon, Désiré Sidibé, Olivier Morel +2
Autonomous robotics is critically affected by the robustness of its scene understanding algorithms. We propose a two-axis pipeline based on polarization indices to analyze dynamic…
P2D: a self-supervised method for depth estimation from polarimetry
Marc Blanchon, Désiré Sidibé, Olivier Morel +3
Monocular depth estimation is a recurring subject in the field of computer vision. Its ability to describe scenes via a depth map while reducing the constraints related to the form…
Polarimetric image augmentation
Marc Blanchon, Olivier Morel, Fabrice Meriaudeau +2
Robotics applications in urban environments are subject to obstacles that exhibit specular reflections hampering autonomous navigation. On the other hand, these reflections are hig…