Improving Time-of-Flight Sensor for Specular Surface with Shape from Polarization

Tomonari Yoshida, Vladislav Golyanik, Oliver Wasenmüller, Didier Stricker

In: IEEE International Conference on Image Processing (ICIP). IEEE International Conference on Image Processing (ICIP-2018) October 7-10 Athens Greece IEEE 2018.


Time-of-Flight (ToF) sensors can obtain depth values for diffuse objects. However, the essential problem is that the sensor can not receive active light from specular surfaces due to specular reflections. In this paper, we propose a new depth reconstruction framework for specular objects that combines ToF cues and Shape from Polarization (SfP). To overcome the ill-posedness of SfP with a single view, we integrate superpixel segmentation with planarity constraints for every superpixel. Experimental results demonstrate the effectiveness of the depth reconstruction algorithm for both controlled environment data and real vehicle data in a parking area.

ICIP_2018_camera_ready.pdf (pdf, 970 KB)

German Research Center for Artificial Intelligence
Deutsches Forschungszentrum für Künstliche Intelligenz