Bernd Jähne — accepted AI-conference papers

2018

Robust Hough Transform Based 3D Reconstruction From Circular Light Fields

Alessandro Vianello, Jens Ackermann, Maximilian Diebold, Bernd Jähne

CVPR 2018poster

Light-field imaging is based on images taken on a regular grid. Thus, high-quality 3D reconstructions are obtainable by analyzing orientations in epipolar plane images (EPIs). Unfortunately, such data only allows to evaluate one side of the object. Moreover, a constant intensity along each orientati…

Cited by 16 Source ↗PDF ↗Scholar ↗

2018

Trust Your Model: Light Field Depth Estimation With Inline Occlusion Handling

Hendrik Schilling, Maximilian Diebold, Carsten Rother, Bernd Jähne

CVPR 2018poster

We address the problem of depth estimation from light-field images. Our main contribution is a new way to handle occlusions which improves general accuracy and quality of object borders. In contrast to all prior work we work with a model which directly incorporates both depth and occlusion, using a…

Cited by 78 Source ↗PDF ↗Scholar ↗