Header logo is

Object Scene Flow for Autonomous Vehicles


Conference Paper



This paper proposes a novel model and dataset for 3D scene flow estimation with an application to autonomous driving. Taking advantage of the fact that outdoor scenes often decompose into a small number of independently moving objects, we represent each element in the scene by its rigid motion parameters and each superpixel by a 3D plane as well as an index to the corresponding object. This minimal representation increases robustness and leads to a discrete-continuous CRF where the data term decomposes into pairwise potentials between superpixels and objects. Moreover, our model intrinsically segments the scene into its constituting dynamic components. We demonstrate the performance of our model on existing benchmarks as well as a novel realistic dataset with scene flow ground truth. We obtain this dataset by annotating 400 dynamic scenes from the KITTI raw data collection using detailed 3D CAD models for all vehicles in motion. Our experiments also reveal novel challenges which can't be handled by existing methods.

Author(s): Moritz Menze and Andreas Geiger
Book Title: IEEE Conf. on Computer Vision and Pattern Recognition (CVPR) 2015
Pages: 3061--3070
Year: 2015
Month: June
Publisher: IEEE

Department(s): Autonomous Vision, Perceiving Systems
Bibtex Type: Conference Paper (inproceedings)
Paper Type: Conference

DOI: 10.1109/CVPR.2015.7298925
Event Name: IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2015
Event Place: Boston, MA, USA

Links: pdf


  title = {Object Scene Flow for Autonomous Vehicles},
  author = {Menze, Moritz and Geiger, Andreas},
  booktitle = { IEEE Conf. on Computer Vision and Pattern Recognition (CVPR) 2015},
  pages = {3061--3070},
  publisher = {IEEE},
  month = jun,
  year = {2015},
  month_numeric = {6}