Automated Scene Flow Data Generation for Training and Verification

Oliver Wasenmüller, René Schuster, Didier Stricker, Karl Leiss, Jürger Pfister, Oleksandra Ganus, Julian Tatsch, Artem Savkin, Nikolas Brasch

In: ACM Computer Science in Cars Symposium (CSCS). ACM Computer Science in Cars Symposium (CSCS-2018) Munich Germany ACM 2018.


Scene flow describes the 3D position as well as the 3D motion of each pixel in an image. Such algorithms are the basis for many state-of-the-art autonomous or automated driving functions. For verification and training large amounts of ground truth data is required, which is not available for real data. In this paper, we demonstrate a technology to create synthetic data with dense and precise scene flow ground truth.

CSCS_data_generation.pdf (pdf, 2 MB )

German Research Center for Artificial Intelligence
Deutsches Forschungszentrum für Künstliche Intelligenz