Recent advances in autonomous driving require more and more highly realistic reference
data, even for difficult situations such as low light and bad weather. We present a new stereo …

Virtual teams, with a high level of interdependence and cooperation among team members,
are one of the building blocks of successful global software organizations. Shared team …

Creating stereo ground truth based on real images is a measurement task. Measurements
are never perfectly accurate: the depth at each pixel follows an error distribution. A common …

Optical flow ground truth generated by computer graphics has many advantages. For
example, we can systematically vary scene parameters to understand algorithm sensitivities …

This thesis investigates performance metrics and test datasets used for the evaluation of
depth estimation algorithms. Stereo and light field algorithms take structured camera images …

This thesis is concerned with the acquisition, modeling, and augmentation of material
reflectance to simulate high-fidelity synthetic data for computer vision tasks. The topic is …

This thesis is concerned with the analysis and modeling of effects which cause errors in
passive stereo and Time-of-Flight imaging systems. The main topics are covered in four …